Search

In the financial field, constructing efficient investment portfolios is a focal point of research, encompassing asset selection and optimization of asset allocation. With the advancements in Large Language Models (LLMs), generative Artificial Intelligence (AI) tools have showcased capabilities never seen before. However, the black-box nature of these tools renders their outputs difficult to interpret directly, often necessitating iterative fine-tuning to align with users' expected outcomes. This study presents a structured prompt framework specifically designed for stock selection, aiming to provide direct and interpretable stock-selecting tools for investors of various levels. By creating representative scenarios and combining them into different cases for experimentation, we can explore how the construction of prompts influences the responses generated by generative AI tools. Additionally, this paper proposes a novel algorithm that combines the Nonlinear-Activated Beetle Antennae Search strategy with the Egret Swarm Optimization Algorithm (NBESOA) to address the Mean-Variance Portfolio Selection problem with Transaction Costs and Cardinality Constraints (MVPS-TCCC), utilizing real stock market data to construct portfolios based on generative AI tools recommendations. Simulation results indicate that, compared to other algorithms, NBESOA prefers optimizing portfolio configurations to achieve the highest Sharpe Ratio with the strictest constraints, bringing the outcomes closer to the portfolio's efficient frontier. [ABSTRACT FROM AUTHOR]

• This study evaluated the artificial intelligence (AI) proficiency of obstetrics residents in clinical scenarios. • This study identified a gap between perceived and actual AI skills. • There is a need for AI literacy in medical education. • Structured AI training programmes in obstetrics are proposed. • This study highlighted the role of AI in enhancing healthcare efficiency. In line with the digital transformation trend in medical training, students may resort to artificial intelligence (AI) for learning. This study assessed the interaction between obstetrics residents and ChatGPT during clinically oriented summative evaluations related to acute hepatic steatosis of pregnancy, and their self-reported competencies in information technology (IT) and AI. The participants in this semi-qualitative observational study were 14 obstetrics residents from two university hospitals. Students' queries were categorized into three distinct types: third-party enquiries; search-engine-style queries; and GPT-centric prompts. Responses were compared against a standardized answer produced by ChatGPT with a Delphi-developed expert prompt. Data analysis employed descriptive statistics and correlation analysis to explore the relationship between AI/IT skills and response accuracy. The study participants showed moderate IT proficiency but low AI proficiency. Interaction with ChatGPT regarding clinical signs of acute hepatic steatosis gravidarum revealed a preference for third-party questioning, resulting in only 21% accurate responses due to misinterpretation of medical acronyms. No correlation was found between AI response accuracy and the residents' self-assessed IT or AI skills, with most expressing dissatisfaction with their AI training. This study underlines the discrepancy between perceived and actual AI proficiency, highlighted by clinically inaccurate yet plausible AI responses – a manifestation of the 'stochastic parrot' phenomenon. These findings advocate for the inclusion of structured AI literacy programmes in medical education, focusing on prompt engineering. These academic skills are essential to exploit AI's potential in obstetrics and gynaecology. The ultimate aim is to optimize patient care in AI-augmented health care, and prevent misleading and unsafe knowledge acquisition. [ABSTRACT FROM AUTHOR]

Objectives Patients are increasingly being given direct access to their medical records. However, radiology reports are written for clinicians and typically contain medical jargon, which can be confusing. One solution is for radiologists to provide a "colloquial" version that is accessible to the layperson. Because manually generating these colloquial translations would represent a significant burden for radiologists, a way to automatically produce accurate, accessible patient-facing reports is desired. We propose a novel method to produce colloquial translations of radiology reports by providing specialized prompts to a large language model (LLM). Materials and Methods Our method automatically extracts and defines medical terms and includes their definitions in the LLM prompt. Using our method and a naive strategy, translations were generated at 4 different reading levels for 100 de-identified neuroradiology reports from an academic medical center. Translations were evaluated by a panel of radiologists for accuracy, likability, harm potential, and readability. Results Our approach translated the Findings and Impression sections at the 8th-grade level with accuracies of 88% and 93%, respectively. Across all grade levels, our approach was 20% more accurate than the baseline method. Overall, translations were more readable than the original reports, as evaluated using standard readability indices. Conclusion We find that our translations at the eighth-grade level strike an optimal balance between accuracy and readability. Notably, this corresponds to nationally recognized recommendations for patient-facing health communication. We believe that using this approach to draft patient-accessible reports will benefit patients without significantly increasing the burden on radiologists. [ABSTRACT FROM AUTHOR]

Process design improvements require extensive knowledge, considerable time, and huge human resources due to the complexity of chemical processes and their diverse objective functions. However, machine learning-based approaches using vast accumulated data are limited in low versatility, applicable only to specific processes, and unable to understand the basis of model decisions. This study proposes the GPT-based Improved Process Hybrid Transformer (GIPHT), a process design improvement generation system utilizing Large Language Model (LLM). LLMs, being natural language-based, allow for understanding the basis of model decisions without need of explainable AI analysis. GIPHT is composed of multi-agent to enhance versatility and performance for diverse chemical processes. We also propose the Detailed Simplified Flowsheet Input Line Entry System format to express process diagrams in natural language, including enhanced information about process conditions. A structured prompt system is employed and validated in the LLM domain through prompt engineering. GIPHT searches and extracts data based on its proposed improvement methodology, providing explanations for the decision-making process and the basis, overcoming limitations of the traditional black-box AI models. It offers directional ideas to design engineers in the early stages of process design and would be used for training of process engineers, supporting improvement of outdated processes and transformation into more environmentally friendly processes. [ABSTRACT FROM AUTHOR]

In the domain of natural language processing, the rise of Large Language Models and Generative AI represents a noteworthy transition, enabling machines to understand and generate text resembling that produced by humans. This research conducts a thorough examination of this transformative technology, with a focus on its influence on machine translation. The study explores the translation landscape between English and Indic languages, which include Hindi, Kannada, Malayalam, Tamil, and Telugu. To address this, the Large Language Model, BLOOMZ-3b, is utilized, which has been primarily developed for a text generation task. Multiple prompting engineering techniques for machine translation are prominently explored. The study further traverse fine-tuning the BLOOMZ-3b model using a Parameter Efficient Fine-Tuning technique called Low Rank Adaptation, aiming to reduce computational complexity. Hence, by combining innovative prompting approaches using BLOOMZ-3b model and fine-tuning the model, it contributes to continuous development of machine translation technologies beyond traditional borders of what can be done with respect to language processing. In this regard, not only does this research shed light on the intricacy of translation problems but it also sets a precedence for optimizing or adapting big language models to various languages which end up advancing Artificial Intelligence and Natural Language Processing at large. [ABSTRACT FROM AUTHOR]

Large Language Models (LLMs) excel in fields such as natural language understanding, generation, complex reasoning, and biomedicine. With advancements in materials science, traditional manual annotation methods for phase diagrams have become inadequate due to their time-consuming nature and limitations in updating thermodynamic databases. To overcome these challenges, we propose a framework based on instruction tuning, utilizing LLMs for automated end-to-end annotation of phase diagrams. High-quality phase diagram images and expert descriptions are collected from handbooks and then preprocessed to correct errors, remove redundancies, and enhance information. These preprocessed data form a golden dataset, from which a subset are used to train LLMs through hierarchical sampling. The fine-tuned LLM is then tested for automated phase diagram annotation. Results show that the fine-tuned model achieves a cosine similarity of 0.8737, improving phase diagram comprehension accuracy by 7% compared to untuned LLMs. To the best of our knowledge, this is the first paper to propose using LLMs for the automated annotation of phase diagrams, replacing traditional manual annotation methods and significantly enhancing efficiency and accuracy. [ABSTRACT FROM AUTHOR]

The use of generative artificial intelligence (AI) in higher education design programmes is expanding, yet there is little formalized approach to its integration. Professionally, generative AI is starting to become an indispensable tool for ideation and prototyping, two fundamental skills taught in design's studio pedagogy. Yet this digital leap into the future risks leaving design educators behind unless they take a proactive approach to its implementation and present its strengths and weaknesses. This study surveyed 74 design students from an Australian university, exploring their current utilization of generative AI and their projections for its future application in design practice. Findings confirm that generative AI is being used in an ad hoc way by students to speed up the ideation process tempered by a sceptical view of its creative output. A list of generative AI training for integration into the design curricula based on current research and survey results is proposed. [ABSTRACT FROM AUTHOR]

Since its release in late 2022, ChatGPT and subsequent generative artificial intelligence (GAI) tools have raised a wide variety of questions and concerns for the field of technical communication: How will these tools be incorporated into professional settings? How might we appropriately integrate these tools into our research and teaching? In this review, we examine research published in 2023–2024 addressing these questions (N = 28). Overall, we find preliminary evidence that GAI tools can positively impact student writing and assessment; they also have the potential to assist with some aspects of academic and medical research and writing. However, there are concerns about their reliability and the ethical conundrums raised when they are used inappropriately or when their outputs cannot be distinguished from humans. More research is needed for evidence-based teaching and research strategies as well as policies guiding ethical use. We offer suggestions for new research avenues and methods. [ABSTRACT FROM AUTHOR]

This study explores how prompting techniques, especially those integrated with rhetorical analysis results, may improve the effectiveness of artificial intelligence (AI)-generated business communication messages. I conducted an experiment to assess the effectiveness of these prompting techniques in the context of crafting a negative message generated with ChatGPT 3.5 (n = 85). A multiple regression was calculated to explore prompting techniques' impact on the negative message grades and how each technique influences the message grade. The results (F (4, 80) = 31.84, p <.001), with an adjusted R 2 =.595, indicate a positive relationship between prompting techniques and the effectiveness of AI-generated messages. This study also identified challenges related to students' AI literacy. I conclude the study by recommending practical measures on how to incorporate AI into business and professional writing classrooms. [ABSTRACT FROM AUTHOR]

Discussions of the use of artificial intelligence (AI) have become ubiquitous in research, industry, and education. Prompt engineering has emerged as a valuable skill desired by employers, and students have begun to express interest in learning effective ways of interacting with Generative AI. While much research has been done to formalize and optimize the process of prompt engineering, few studies have investigated the use of AI by nonexperts, including nonexpert teachers. In this study, we use qualitative analysis to characterize the process by which nonexpert teachers engage with and learn from ChatGPT as they engage with it as co-creators to develop an educational game designed to teach concepts of financial literacy. We address implications for nonexpert teachers' use of Generative AI, including suggested methods for the use of ChatGPT to develop educational games and for tacitly learning prompt engineering by using the tool. [ABSTRACT FROM AUTHOR]

Artificial intelligence (AI) research aims to model the way human thinking works, in an attempt to reproduce abilities such as learning, decision-making and problem-solving. The concept of artificial intelligence is not a new one, research on it began in the 1950s when Alan Turing formulated the Turing test, a test to measure the intelligence of a machine. Major milestones in AI research include the creation of the first artificial neural networks in the 1950s and the first game programs in the 1960s. In the 1970s, the algorithms and techniques that still form the basis of AI today, such as machine learning and symbolic AI, began to emerge. The real breakthrough came with the integration of AI into everyday use in the 1990s and early 2000s. With the rise of the internet and the digitalization of data, AI has spread to a wide range of areas, including internet search engines, recommendation systems, online shopping algorithms and virtual assistants in smartphones. In the 2010s, AI continued to make significant progress in areas such as autonomous vehicles, medicine and robotics. AIbased language models, such as the GPT-3.5 used by ChatGPT, later upgraded to GPT-4 base models, published in November 2022, are increasingly becoming part of our daily lives and across industries are being used in a growing number of fields to facilitate intelligent communication and humanmachine interaction. In this paper, we are focusing on AI-based support for teachers. We will explore areas where AI can be effectively used to increase the efficiency of teachers' work, enumerating some AIbased solutions that can greatly contribute to relieving teachers of their daily routine tasks. [ABSTRACT FROM AUTHOR]

Survey data play a crucial role in various research fields, including economics, education, and healthcare, by providing insights into human behavior and opinions. However, item non-response, where respondents fail to answer specific questions, presents a significant challenge by creating incomplete datasets that undermine data integrity and can hinder or even prevent accurate analysis. Traditional methods for addressing missing data, such as statistical imputation techniques and deep learning models, often fall short when dealing with the rich linguistic content of survey data. These approaches are also hampered by high time complexity for training and the need for extensive preprocessing or feature selection. In this paper, we introduce an approach that leverages Large Language Models (LLMs) through prompt engineering for predicting item non-responses in survey data. Our method combines the strengths of both traditional imputation techniques and deep learning methods with the advanced linguistic understanding of LLMs. By integrating respondent similarities, question relevance, and linguistic semantics, our approach enhances the accuracy and comprehensiveness of survey data analysis. The proposed method bypasses the need for complex preprocessing and additional training, making it adaptable, scalable, and capable of generating explainable predictions in natural language. We evaluated the effectiveness of our LLM-based approach through a series of experiments, demonstrating its competitive performance against established methods such as Multivariate Imputation by Chained Equations (MICE), MissForest, and deep learning models like TabTransformer. The results show that our approach not only matches but, in some cases, exceeds the performance of these methods while significantly reducing the time required for data processing. [ABSTRACT FROM AUTHOR]

The article presents work on developing a software application for test creation using artificial intelligence and large language models. Its main goal is to optimize the educators' work by automating the process of test generation and evaluation, with the tests being stored for subsequent analysis and use. The application can generate test questions based on specified criteria such as difficulty level, Bloom's taxonomy level, question type, style and format, feedback inclusion, and more, thereby providing opportunities to enhance the adaptability and efficiency of the learning process. It is developed on the Google Firebase platform, utilizing the ChatGPT API, and also incorporates cloud computing to ensure scalability and data reliability. [ABSTRACT FROM AUTHOR]

Pre-trained transformer models shine in many natural language processing tasks and therefore are expected to bear the representation of the input sentence or text meaning. These sentence-level embeddings are also important in retrieval-augmented generation. But do commonly used plain averaging or prompt templates sufficiently capture and represent the underlying meaning? After providing a comprehensive review of existing sentence embedding extraction and refinement methods, we thoroughly test different combinations and our original extensions of the most promising ones on pretrained models. Namely, given 110 M parameters, BERT's hidden representations from multiple layers, and many tokens, we try diverse ways to extract optimal sentence embeddings. We test various token aggregation and representation post-processing techniques. We also test multiple ways of using a general Wikitext dataset to complement BERT's sentence embeddings. All methods are tested on eight Semantic Textual Similarity (STS), six short text clustering, and twelve classification tasks. We also evaluate our representation-shaping techniques on other static models, including random token representations. Proposed representation extraction methods improve the performance on STS and clustering tasks for all models considered. Very high improvements for static token-based models, especially random embeddings for STS tasks, almost reach the performance of BERT-derived representations. Our work shows that the representation-shaping techniques significantly improve sentence embeddings extracted from BERT-based and simple baseline models. [ABSTRACT FROM AUTHOR]

Large language models have demonstrated impressive capabilities. The recent research conducted in the field of prompt engineering showed that their base performance is just a glimpse of their full abilities. Enhanced with auxiliary tools and provided with examples of how to solve the tasks, their adoption into our applications seems trivial. In this context, we ask an uncomfortable question. Are the models secure enough to be adopted in our systems, or do they represent Trojan horses? The idea of prompt injection and jailbreak attacks does not seem to bother the adopters too much. Even though there are a lot of studies that look into the benefits of the prompting techniques, none address their possible downside in regard to the security. We want take a step further and investigate the impact of the most popular prompting techniques on this aspect of large language models and implicitly the systems to which they belong. Using three of the most deployed GPT models to date, we conducted a few of the most popular attacks in different setup scenarios and demonstrate that prompting techniques can have a negative impact on the security of the LLMs. More than that, they also expose other system components that otherwise would have been less exposed. In the end, we try to come up with possible solutions and present future research perspectives. [ABSTRACT FROM AUTHOR]

Objectives Large Language Models (LLMs) have been proposed as a solution to address high volumes of Patient Medical Advice Requests (PMARs). This study addresses whether LLMs can generate high quality draft responses to PMARs that satisfies both patients and clinicians with prompt engineering. Materials and Methods We designed a novel human-involved iterative processes to train and validate prompts to LLM in creating appropriate responses to PMARs. GPT-4 was used to generate response to the messages. We updated the prompts, and evaluated both clinician and patient acceptance of LLM-generated draft responses at each iteration, and tested the optimized prompt on independent validation data sets. The optimized prompt was implemented in the electronic health record production environment and tested by 69 primary care clinicians. Results After 3 iterations of prompt engineering, physician acceptance of draft suitability increased from 62% to 84% (P  <.001) in the validation dataset (N  = 200), and 74% of drafts in the test dataset were rated as "helpful." Patients also noted significantly increased favorability of message tone (78%) and overall quality (80%) for the optimized prompt compared to the original prompt in the training dataset, patients were unable to differentiate human and LLM-generated draft PMAR responses for 76% of the messages, in contrast to the earlier preference for human-generated responses. Majority (72%) of clinicians believed it can reduce cognitive load in dealing with InBasket messages. Discussion and Conclusion Informed by clinician and patient feedback synergistically, tuning in LLM prompt alone can be effective in creating clinically relevant and useful draft responses to PMARs. [ABSTRACT FROM AUTHOR]

The rapid advancements in natural language processing, particularly with the development of Generative Pre-trained Transformer (GPT) models, have opened up new avenues for researchers across various domains. This review article explores the potential of GPT as a research tool, focusing on the core functionalities, key features, and real-world applications of the GPT-4 model. We delve into the concept of prompt engineering, a crucial technique for effectively utilizing GPT, and provide guidelines for designing optimal prompts. Through case studies, we demonstrate how GPT can be applied at various stages of the research process, including literature review, data analysis, and manuscript preparation. The utilization of GPT is expected to enhance research efficiency, stimulate creative thinking, facilitate interdisciplinary collaboration, and increase the impact of research findings. However, it is essential to view GPT as a complementary tool rather than a substitute for human expertise, keeping in mind its limitations and ethical considerations. As GPT continues to evolve, researchers must develop a deep understanding of this technology and leverage its potential to advance their research endeavors while being mindful of its implications. [ABSTRACT FROM AUTHOR]

Copyright of China Medical Education Technology is the property of China Medical Education Technology Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Knowledge creation in education is a critical practice for advancing collective knowledge and fostering innovation within a student community. Students play vital roles in identifying gaps and collaborative work to improve community ideas from discourse, but idea quality can be suboptimal, affected by a lack of resources or diversity of ideas. The use of generative Artificial Intelligence and large language models (LLMs) in education has allowed work on idea-centric discussions to advance in ways that were previously unfeasible. However, the use of LLMs requires specific skill sets in prompt engineering, relevant to the in-context technique known as Chain-of-Thought (CoT) for generating and supporting improvable ideas in student discourse. A total of 721 discourse turns consisting of 272 relevant question–answer pairs and 149 threads of student discourse data were collected from 31 students during a two-day student Knowledge Building Design Studio (sKBDS). Student responses were augmented using the CoT approach and the LLM-generated responses were compared with students' original responses. Findings are illustrated using two threads to show that CoT-augmented inputs for the LLMs can generate responses that support improvable ideas in the context of knowledge creation. This study presents work from authentic student discourse and has implications for research and classroom practice. [ABSTRACT FROM AUTHOR]

Large language models (LLMs) are sophisticated AI-driven models trained on vast sources of natural language data. They are adept at generating responses that closely mimic human conversational patterns. One of the most notable examples is OpenAI's ChatGPT, which has been extensively used across diverse sectors. Despite their flexibility, a significant challenge arises as most users must transmit their data to the servers of companies operating these models. Utilizing ChatGPT or similar models online may inadvertently expose sensitive information to the risk of data breaches. Therefore, implementing LLMs that are open source and smaller in scale within a secure local network becomes a crucial step for organizations where ensuring data privacy and protection has the highest priority, such as regulatory agencies. As a feasibility evaluation, we implemented a series of open-source LLMs within a regulatory agency's local network and assessed their performance on specific tasks involving extracting relevant clinical pharmacology information from regulatory drug labels. Our research shows that some models work well in the context of few- or zero-shot learning, achieving performance comparable, or even better than, neural network models that needed thousands of training samples. One of the models was selected to address a real-world issue of finding intrinsic factors that affect drugs' clinical exposure without any training or fine-tuning. In a dataset of over 700 000 sentences, the model showed a 78.5% accuracy rate. Our work pointed to the possibility of implementing open-source LLMs within a secure local network and using these models to perform various natural language processing tasks when large numbers of training examples are unavailable. [ABSTRACT FROM AUTHOR]

Without writing a single line of code by a human, an example Monte Carlo simulation-based application for stochastic dependence modeling with copulas is developed through pair programming involving a human partner and a large language model (LLM) fine-tuned for conversations. This process encompasses interacting with ChatGPT using both natural language and mathematical formalism. Under the careful supervision of a human expert, this interaction facilitated the creation of functioning code in MATLAB, Python, and R. The code performs a variety of tasks including sampling from a given copula model, evaluating the model's density, conducting maximum likelihood estimation, optimizing for parallel computing on CPUs and GPUs, and visualizing the computed results. In contrast to other emerging studies that assess the accuracy of LLMs like ChatGPT on tasks from a selected area, this work rather investigates ways how to achieve a successful solution of a standard statistical task in a collaboration of a human expert and artificial intelligence (AI). Particularly, through careful prompt engineering, we separate successful solutions generated by ChatGPT from unsuccessful ones, resulting in a comprehensive list of related pros and cons. It is demonstrated that if the typical pitfalls are avoided, we can substantially benefit from collaborating with an AI partner. For example, we show that if ChatGPT is not able to provide a correct solution due to a lack of or incorrect knowledge, the human-expert can feed it with the correct knowledge, e.g., in the form of mathematical theorems and formulas, and make it to apply the gained knowledge in order to provide a correct solution. Such ability presents an attractive opportunity to achieve a programmed solution even for users with rather limited knowledge of programming techniques. [ABSTRACT FROM AUTHOR]

Large Language Models (LLMs have the potential to revolutionize clinical medicine by enhancing healthcare access, diagnosis, surgical planning, and education. However, their utilization requires careful, prompt engineering to mitigate challenges like hallucinations and biases. Proper utilization of LLMs involves understanding foundational concepts such as tokenization, embeddings, and attention mechanisms, alongside strategic prompting techniques to ensure accurate outputs. For innovative healthcare solutions, it is essential to maintain ongoing collaboration between AI technology and medical professionals. Ethical considerations, including data security and bias mitigation, are critical to their application. By leveraging LLMs as supplementary resources in research and education, we can enhance learning and support knowledge-based inquiries, ultimately advancing the quality and accessibility of medical care. Continued research and development are necessary to fully realize the potential of LLMs in transforming healthcare. [ABSTRACT FROM AUTHOR]

Background Chat Generative Pre-trained Transformer (ChatGPT) and other ChatBots have emerged as tools for interacting with information in manners resembling natural human speech. Consequently, the technology is used across various disciplines, including business, education, and even in biomedical sciences. There is a need to better understand how ChatGPT can be used to advance gerontology research. Therefore, we evaluated ChatGPT responses to questions on specific topics in gerontology research, and brainstormed recommendations for its use in the field. Methods We conducted semistructured brainstorming sessions to identify uses of ChatGPT in gerontology research. We divided a team of multidisciplinary researchers into 4 topical groups: (a) gero-clinical science, (b) basic geroscience, (c) informatics as it relates to electronic health records, and (d) gero-technology. Each group prompted ChatGPT on a theory-, methods-, and interpretation-based question and rated responses for accuracy and completeness based on standardized scales. Results ChatGPT responses were rated by all groups as generally accurate. However, the completeness of responses was rated lower, except by members of the informatics group, who rated responses as highly comprehensive. Conclusions ChatGPT accurately depicts some major concepts in gerontological research. However, researchers have an important role in critically appraising the completeness of its responses. Having a single generalized resource like ChatGPT may help summarize the preponderance of evidence in the field to identify gaps in knowledge and promote cross-disciplinary collaboration. [ABSTRACT FROM AUTHOR]

Copyright of Procesamiento del Lenguaje Natural is the property of Sociedad Espanola para el Procesamiento del Lenguaje Natural and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Unbelievable progress in creating real-looking texts, audios and videos, numerous product designs and templates using generative artificial intelligence (GenAI)-enabled technologies have made work easier. However, they have their possible ill-effects too. Since the fruition of regulatory framework trails technological evolution, the future can see a virus-antivirus kind of ecosystem, where one set of GenAI tools will create contents that look most authentic and evade plagiarism and the other set will be busy trapping those. This study delves deep into the working of GenAI, various industry use cases, risk paradigms, and how organizations can start adopting the same, as it may be impossible to deny GenAI's business benefits for long. [ABSTRACT FROM AUTHOR]

The rapid advances in generative artificial intelligence (AI) open up attractive opportunities for creative problem-solving through human-guided AI partnerships. To explore this potential, we initiated a crowdsourcing challenge focused on sustainable, circular economy business ideas generated by the human crowd (HC) and collaborative human-AI efforts using two alternative forms of solution search. The challenge attracted 125 global solvers from various industries, and we used strategic prompt engineering to generate the human-AI solutions. We recruited 300 external human evaluators to judge a randomized selection of 13 out of 234 solutions, totaling 3,900 evaluator-solution pairs. Our results indicate that while human crowd solutions exhibited higher novelty—both on average and for highly novel outcomes—human-AI solutions demonstrated superior strategic viability, financial and environmental value, and overall quality. Notably, human-AI solutions cocreated through differentiated search, where human-guided prompts instructed the large language model to sequentially generate outputs distinct from previous iterations, outperformed solutions generated through independent search. By incorporating "AI in the loop" into human-centered creative problem-solving, our study demonstrates a scalable, cost-effective approach to augment the early innovation phases and lays the groundwork for investigating how integrating human-AI solution search processes can drive more impactful innovations. Funding: This work was supported by Harvard Business School (Division of Research and Faculty Development) and the Laboratory for Innovation Science at Harvard (LISH) at the Digital Data and Design (D3) Institute at Harvard. Supplemental Material: The online appendix is available at https://doi.org/10.1287/orsc.2023.18430. [ABSTRACT FROM AUTHOR]

The advent of blockchain technology has revolutionized various sectors by providing transparency, immutability, and automation. Central to this revolution are smart contracts, which facilitate trustless and automated transactions across diverse domains. However, the proliferation of smart contracts has exposed significant security vulnerabilities, necessitating advanced analysis techniques. Data dependency analysis is a critical program analysis method used to enhance the testing and security of smart contracts. This paper introduces Sligpt, an innovative methodology that integrates a large language model (LLM), specifically GPT-4o, with the static analysis tool Slither, to perform data dependency analyses on Solidity smart contracts. Our approach leverages both the advanced code comprehension capabilities of GPT-4o and the advantages of a traditional analysis tool. We empirically evaluate Sligpt using a curated dataset of Ethereum smart contracts. Sligpt achieves significant improvements in precision, recall, and overall analysis depth compared with Slither and GPT-4o, providing a robust solution for data dependency analysis. This paper also discusses the challenges encountered, such as the computational resource requirements and the inherent variability in LLM outputs, while proposing future research directions to further enhance the methodology. Sligpt represents a significant advancement in the field of static analysis on smart contracts, offering a practical framework for integrating LLMs with static analysis tools. [ABSTRACT FROM AUTHOR]

One of the most common questions that students ask statistics advisors is 'What test should I do?' This paper explores the use of generative AI chatbots, specifically ChatGPT, as a tool to assist students, in particular those with limited experience in statistics, in selecting appropriate statistical tests for their analyses. Traditional methods, such as flowcharts and online test selectors, require at least a basic understanding of measurement scales and research design, which can be an issue for many students who have limited exposure to statistics on their courses. This research focuses on developing and refining prompts to guide ChatGPT in providing accurate and relevant statistical test recommendations. A hypothetical scenario was used to test the effectiveness of various prompts, ranging from simple, naïve questions to more sophisticated ones utilising specific prompt patterns, such as the 'context manager' and 'flipped interaction.' These patterns were selected to enhance the chatbot's responses and ensure the relevance and accuracy of the test suggestions. The findings suggest that while AI chatbots like ChatGPT can be a valuable resource for students, their effectiveness is highly dependent on the quality of the prompts used. The paper concludes with a discussion on the potential of these AI tools in educational settings, acknowledging the limitations of current technology and suggesting directions for future research and development. [ABSTRACT FROM AUTHOR]

Importance The study highlights the potential of large language models, specifically GPT-3.5 and GPT-4, in processing complex clinical data and extracting meaningful information with minimal training data. By developing and refining prompt-based strategies, we can significantly enhance the models' performance, making them viable tools for clinical NER tasks and possibly reducing the reliance on extensive annotated datasets. Objectives This study quantifies the capabilities of GPT-3.5 and GPT-4 for clinical named entity recognition (NER) tasks and proposes task-specific prompts to improve their performance. Materials and Methods We evaluated these models on 2 clinical NER tasks: (1) to extract medical problems, treatments, and tests from clinical notes in the MTSamples corpus, following the 2010 i2b2 concept extraction shared task, and (2) to identify nervous system disorder-related adverse events from safety reports in the vaccine adverse event reporting system (VAERS). To improve the GPT models' performance, we developed a clinical task-specific prompt framework that includes (1) baseline prompts with task description and format specification, (2) annotation guideline-based prompts, (3) error analysis-based instructions, and (4) annotated samples for few-shot learning. We assessed each prompt's effectiveness and compared the models to BioClinicalBERT. Results Using baseline prompts, GPT-3.5 and GPT-4 achieved relaxed F1 scores of 0.634, 0.804 for MTSamples and 0.301, 0.593 for VAERS. Additional prompt components consistently improved model performance. When all 4 components were used, GPT-3.5 and GPT-4 achieved relaxed F1 socres of 0.794, 0.861 for MTSamples and 0.676, 0.736 for VAERS, demonstrating the effectiveness of our prompt framework. Although these results trail BioClinicalBERT (F1 of 0.901 for the MTSamples dataset and 0.802 for the VAERS), it is very promising considering few training samples are needed. Discussion The study's findings suggest a promising direction in leveraging LLMs for clinical NER tasks. However, while the performance of GPT models improved with task-specific prompts, there's a need for further development and refinement. LLMs like GPT-4 show potential in achieving close performance to state-of-the-art models like BioClinicalBERT, but they still require careful prompt engineering and understanding of task-specific knowledge. The study also underscores the importance of evaluation schemas that accurately reflect the capabilities and performance of LLMs in clinical settings. Conclusion While direct application of GPT models to clinical NER tasks falls short of optimal performance, our task-specific prompt framework, incorporating medical knowledge and training samples, significantly enhances GPT models' feasibility for potential clinical applications. [ABSTRACT FROM AUTHOR]

Since ChatGPT exploded onto the scene in October 2022, the media has been breathless with their discussion about how it is going to impact many aspects of life and work. In order to bring this new reality of generative AI into the Introduction to Management Information Systems classroom at both the undergraduate and graduate levels, we have developed two short cases that can be completed in or out of the classroom. These cases allow students to use generative AI for an interesting and useful purpose and develop prompts to deliver the output. Students can begin to learn what generative AI can do for them, and how it can shape their future careers. We tested the perceived effectiveness of the project on students using a pre/post survey. The results are analyzed using a paired t-test and demonstrate that students increased their understanding of generative AI and prompt engineering. [ABSTRACT FROM AUTHOR]

In recent years, the integration of large language models (LLMs) has revolutionized the field of robotics, enabling robots to communicate, understand, and reason with human-like proficiency. This paper explores the multifaceted impact of LLMs on robotics, addressing key challenges and opportunities for leveraging these models across various domains. By categorizing and analyzing LLM applications within core robotics elements—communication, perception, planning, and control—we aim to provide actionable insights for researchers seeking to integrate LLMs into their robotic systems. Our investigation focuses on LLMs developed post-GPT-3.5, primarily in text-based modalities while also considering multimodal approaches for perception and control. We offer comprehensive guidelines and examples for prompt engineering, facilitating beginners' access to LLM-based robotics solutions. Through tutorial-level examples and structured prompt construction, we illustrate how LLM-guided enhancements can be seamlessly integrated into robotics applications. This survey serves as a roadmap for researchers navigating the evolving landscape of LLM-driven robotics, offering a comprehensive overview and practical guidance for harnessing the power of language models in robotics development. [ABSTRACT FROM AUTHOR]

This research explores the guided experimental implementation of ChatGPT as a tool for developing teachers' skills in teaching English. The intervention involved 24 in-service English as a Foreign Language (EFL) teachers who engaged in crafting activities and assessments using researcher-designed prompts. Utilizing a mixed-methods approach, the researchers assessed the participants' ChatGPT integration proficiency through a custom-designed assessment tool aligned with the technological pedagogical content knowledge framework. The eight-week intervention introduced educators to various applications of ChatGPT in EFL teaching, including lesson planning. A quantitative analysis revealed statistically significant improvements in the teachers' ChatGPT integration proficiency across all measured dimensions. The qualitative findings highlight the perceived benefits, challenges, and future prospects of ChatGPT in EFL education. While the practical significance of the improvement was modest, the results suggest that the guided integration of generative chatbots can bolster teachers' ability to leverage this technology appropriately. This study contributes to the limited body of empirical research on integrating large language models into teaching and offers insights into the practical applications and challenges of using ChatGPT in EFL contexts. [ABSTRACT FROM AUTHOR]

Harnessing the power of Large Language Models (LLMs), this study explores the use of three state-of-the-art LLMs, specifically GPT-3.5-turbo, LLaMA3-8B, and LLaMA3-70B, for crash severity analysis and inference, framing it as a classification task. We generate textual narratives from original traffic crash tabular data using a pre-built template infused with domain knowledge. Additionally, we incorporated Chain-of-Thought (CoT) reasoning to guide the LLMs in analyzing the crash causes and then inferring the severity. This study also examine the impact of prompt engineering specifically designed for crash severity inference. The LLMs were tasked with crash severity inference to: (1) evaluate the models' capabilities in crash severity analysis, (2) assess the effectiveness of CoT and domain-informed prompt engineering, and (3) examine the reasoning abilities with the CoT framework. Our results showed that LLaMA3-70B consistently outperformed the other models, particularly in zero-shot settings. The CoT and Prompt Engineering techniques significantly enhanced performance, improving logical reasoning and addressing alignment issues. Notably, the CoT offers valuable insights into LLMs' reasoning process, unleashing their capacity to consider diverse factors such as environmental conditions, driver behavior, and vehicle characteristics in severity analysis and inference. [ABSTRACT FROM AUTHOR]

Aiming at the problems of insufficient model input information and poor reasoning performance in knowledge-based visual question answering (VQA), this paper constructs a PTCR knowledge-based VQA framework based on large language model (LLM), which consists of four parts: answer candidate generation, targeted image descriptions, autonomous chain of thought (CoT) construction, and prompted LLM inference. The PTCR framework uses LLM to guide multimodal large language models to generate targeted image descriptions, which solves the problem of incomplete coverage of previous image captions. It improves the model??s reasoning ability by guiding LLM to autonomously generate CoT, which provides the thinking process of similar problems during the reasoning process; and it introduces selection rearrangement technology to eliminate LLM??s selection location discrimination during the reasoning process, and reduces the randomness error of the reasoning by means of majority voting. Experimental results show that the accuracy of the CogVLM model enhanced by the PTCR framework is improved by 16.7 percentage points and 13.3 percentage points on the OK-VQA and A-OKVQA datasets. Meanwhile, compared with Prophet, the accuracy of the PTCR framework is improved by 3.4 percentage points and 5.0 percentage points on the OK-VQA and A-OKVQA datasets. The results of ablation experiments demonstrate that the methods used in this paper, such as targeted image descriptions and autonomous chains of thought, are all effective in improving accuracy. It is evident that the PTCR framework has improved the performance of knowledge-based VQA.

This essay critically examines some limitations and misconceptions of Large Language Models (LLMs) in relation to knowledge and self-knowledge, particularly in the context of social sciences and humanities (SSH) research. Using an experimental approach, we evaluate the self-consistency of LLM responses by introducing variations in prompts during knowledge retrieval tasks. Our results indicate that self-consistency tends to align with correct responses, yet errors persist, questioning the reliability of LLMs as “knowing” agents. Drawing on epistemological frameworks, we argue that LLMs exhibit the capacity to know only when random factors, or epistemic luck, can be excluded, yet they lack self-awareness of their inconsistencies. Whereas human ignorance often involves many “known unknowns”, LLMs exhibit a form of ignorance manifested through inconsistency, where the ignorance remains a complete “unknown unknown”. LLMs always “assume” they “know”. We repurpose these insights into a pedagogical experiment, encouraging SSH scholars and students to critically engage with LLMs in educational settings. We propose a hands-on approach based on critical technical practice, aiming to balance the practical utility with an informed understanding of their limitations. This approach equips researchers with the skills to use LLMs effectively while promoting a deeper understanding of their operational principles and epistemic constraints.

Abstract The extraction of biological regulation events has been a key focus in the field of biomedical nature language processing (BioNLP). However, existing methods often encounter challenges such as cascading errors in text mining pipelines and limitations in topic coverage from the selected corpus. Fortunately, the emergence of large language models (LLMs) presents a potential solution due to their robust semantic understanding and extensive knowledge base. To explore this potential, our project at the Biomedical Linked Annotation Hackathon 8 (BLAH 8) investigates the feasibility of using LLMs to extract biological regulation events. Our findings, based on the analysis of rice literature, demonstrate the promising performance of LLMs in this task, while also highlighting several concerns that must be addressed in future LLM-based application in low-resource topic.

Abstract In the domain of natural language processing, the rise of Large Language Models and Generative AI represents a noteworthy transition, enabling machines to understand and generate text resembling that produced by humans. This research conducts a thorough examination of this transformative technology, with a focus on its influence on machine translation. The study explores the translation landscape between English and Indic languages, which include Hindi, Kannada, Malayalam, Tamil, and Telugu. To address this, the Large Language Model, BLOOMZ-3b, is utilized, which has been primarily developed for a text generation task. Multiple prompting engineering techniques for machine translation are prominently explored. The study further traverse fine-tuning the BLOOMZ-3b model using a Parameter Efficient Fine-Tuning technique called Low Rank Adaptation, aiming to reduce computational complexity. Hence, by combining innovative prompting approaches using BLOOMZ-3b model and fine-tuning the model, it contributes to continuous development of machine translation technologies beyond traditional borders of what can be done with respect to language processing. In this regard, not only does this research shed light on the intricacy of translation problems but it also sets a precedence for optimizing or adapting big language models to various languages which end up advancing Artificial Intelligence and Natural Language Processing at large.

The advent of blockchain technology has revolutionized various sectors by providing transparency, immutability, and automation. Central to this revolution are smart contracts, which facilitate trustless and automated transactions across diverse domains. However, the proliferation of smart contracts has exposed significant security vulnerabilities, necessitating advanced analysis techniques. Data dependency analysis is a critical program analysis method used to enhance the testing and security of smart contracts. This paper introduces Sligpt, an innovative methodology that integrates a large language model (LLM), specifically GPT-4o, with the static analysis tool Slither, to perform data dependency analyses on Solidity smart contracts. Our approach leverages both the advanced code comprehension capabilities of GPT-4o and the advantages of a traditional analysis tool. We empirically evaluate Sligpt using a curated dataset of Ethereum smart contracts. Sligpt achieves significant improvements in precision, recall, and overall analysis depth compared with Slither and GPT-4o, providing a robust solution for data dependency analysis. This paper also discusses the challenges encountered, such as the computational resource requirements and the inherent variability in LLM outputs, while proposing future research directions to further enhance the methodology. Sligpt represents a significant advancement in the field of static analysis on smart contracts, offering a practical framework for integrating LLMs with static analysis tools.

Knowledge creation in education is a critical practice for advancing collective knowledge and fostering innovation within a student community. Students play vital roles in identifying gaps and collaborative work to improve community ideas from discourse, but idea quality can be suboptimal, affected by a lack of resources or diversity of ideas. The use of generative Artificial Intelligence and large language models (LLMs) in education has allowed work on idea-centric discussions to advance in ways that were previously unfeasible. However, the use of LLMs requires specific skill sets in prompt engineering, relevant to the in-context technique known as Chain-of-Thought (CoT) for generating and supporting improvable ideas in student discourse. A total of 721 discourse turns consisting of 272 relevant question–answer pairs and 149 threads of student discourse data were collected from 31 students during a two-day student Knowledge Building Design Studio (sKBDS). Student responses were augmented using the CoT approach and the LLM-generated responses were compared with students’ original responses. Findings are illustrated using two threads to show that CoT-augmented inputs for the LLMs can generate responses that support improvable ideas in the context of knowledge creation. This study presents work from authentic student discourse and has implications for research and classroom practice.

“Are we asking the right questions?” seems cliché, but for ChatGPT, it is a pivotal tool to ensure the accuracy of responses. While ChatGPT-3.5’s training on the vast database promises to revolutionize STEM education and research, this investigation shows the importance of precise communication and prompt engineering in guiding ChatGPT-3.5 toward reliable and accurate responses, particularly in chemistry. For instance, emphasizing context, clearly defining symbols, and focusing on field-specific instructions can dramatically improve its performance. Furthermore, avoiding open-ended prompts and strategically using repetition can further enhance its accuracy. The iterative prompt design, demonstrated through a series of adjustments, illustrates how seemingly minor refinements, such as substituting “least” for “lowest”, profoundly impact the output. This study highlights the essential role of human oversight, including the construction of well-crafted prompts, in guarding reliable information and nurturing a productive “Human–AI” (HAI) partnership.

Abstract Entity Resolution (ER) is the problem of semi-automatically determining when two entities refer to the same underlying entity, with applications ranging from healthcare to e-commerce. Traditional ER solutions required considerable manual expertise, including domain-specific feature engineering, as well as identification and curation of training data. Recently released large language models (LLMs) provide an opportunity to make ER more seamless and domain-independent. Because of LLMs’ pre-trained knowledge, the matching step in ER can be made easier by just prompting. However, it is also well known that LLMs can pose risks, that the quality of their outputs can depend on how prompts are engineered, and that the cost of using LLMs can be significant. Unfortunately, a systematic experimental study on the effects of different prompting methods and their respective cost for solving domain-specific entity matching using LLMs, like ChatGPT, has been lacking thus far. This paper aims to address this gap by conducting such a study. We consider some relatively simple and cost-efficient ER prompt engineering methods and apply them to perform product matching on two real-world datasets widely used in the community. We select two well-known e-commerce datasets and provide extensive experimental results to show that an LLM like GPT3.5 is viable for high-performing product matching and, interestingly, that more complicated and detailed (and hence, expensive) prompting methods do not necessarily outperform simpler approaches. We provide brief discussions on qualitative and error analysis, including a study of the inter-consistency of different prompting methods to determine whether they yield stable outputs. Finally, we consider some limitations of LLMs when used as a product matcher in potential real-world e-commerce applications.

Abstract This study was designed to assess how different prompt engineering techniques, specifically direct prompts, Chain of Thought (CoT), and a modified CoT approach, influence the ability of GPT-3.5 to answer clinical and calculation-based medical questions, particularly those styled like the USMLE Step 1 exams. To achieve this, we analyzed the responses of GPT-3.5 to two distinct sets of questions: a batch of 1000 questions generated by GPT-4, and another set comprising 95 real USMLE Step 1 questions. These questions spanned a range of medical calculations and clinical scenarios across various fields and difficulty levels. Our analysis revealed that there were no significant differences in the accuracy of GPT-3.5's responses when using direct prompts, CoT, or modified CoT methods. For instance, in the USMLE sample, the success rates were 61.7% for direct prompts, 62.8% for CoT, and 57.4% for modified CoT, with a p-value of 0.734. Similar trends were observed in the responses to GPT-4 generated questions, both clinical and calculation-based, with p-values above 0.05 indicating no significant difference between the prompt types. The conclusion drawn from this study is that the use of CoT prompt engineering does not significantly alter GPT-3.5's effectiveness in handling medical calculations or clinical scenario questions styled like those in USMLE exams. This finding is crucial as it suggests that performance of ChatGPT remains consistent regardless of whether a CoT technique is used instead of direct prompts. This consistency could be instrumental in simplifying the integration of AI tools like ChatGPT into medical education, enabling healthcare professionals to utilize these tools with ease, without the necessity for complex prompt engineering.

Abstract The body of ecological literature, which informs much of our knowledge of the global loss of biodiversity, has been experiencing rapid growth in recent decades. The increasing difficulty of synthesising this literature manually has simultaneously resulted in a growing demand for automated text mining methods. Within the domain of deep learning, large language models (LLMs) have been the subject of considerable attention in recent years due to great leaps in progress and a wide range of potential applications; however, quantitative investigation into their potential in ecology has so far been lacking. In this work, we analyse the ability of GPT‐4 to extract information about invertebrate pests and pest controllers from abstracts of articles on biological pest control, using a bespoke, zero‐shot prompt. Our results show that the performance of GPT‐4 is highly competitive with other state‐of‐the‐art tools used for taxonomic named entity recognition and geographic location extraction tasks. On a held‐out test set, we show that species and geographic locations are extracted with F1‐scores of 99.8% and 95.3%, respectively, and highlight that the model can effectively distinguish between ecological roles of interest such as predators, parasitoids and pests. Moreover, we demonstrate the model's ability to effectively extract and predict taxonomic information across various taxonomic ranks. However, we do report a small number of cases of fabricated information (confabulations). Due to a lack of specialised, pre‐trained ecological language models, general‐purpose LLMs may provide a promising way forward in ecology. Combined with tailored prompt engineering, such models can be employed for a wide range of text mining tasks in ecology, with the potential to greatly reduce time spent on manual screening and labelling of the literature.

Large language models and vision-language models have demonstrated significant potential in various downstream applications, making it become a research hotspot. However, the issues such as hallucinations and knowledge transfer impact the performance of these models. Firstly, this paper explores the fundamental principles of prompt engineering and alignment techniques, and proposes the concept of "prescriptive", which is based on optimizing prompts and expert feedback verification and can be adjusted in real-time. This aims to further enhance the performance of large language models in cross-domain applications. Secondly, the core technologies of prompt engineering, such as the principles of multi-step reasoning for handling complex tasks, are analyzed in depth. Additionally, the development status of prompt engineering is discussed based on practical applications in various fields. Finally, this paper summarizes the challenges faced by prompt engineering and looks into its future development directions. The development of prompt engineering in theory and application, provide comprehensive solutions for improving the performance of large models in practical applications.

ChatGPT, a widely used Large Language Model (LLM), enhances productivity in various sectors, including education. However, its extensive usage often lacks proficiency in writing effective prompts, resulting in less optimal, biased, and hallucinated outputs. This community service initiative by Universitas Muhammadiyah Malang (UMM) aims to educate teachers on prompt engineering, enabling them to (i) write effective prompts to utilize ChatGPT's potential, (ii) educate about potential biases and hallucinations of ChatGPT, and (iii) integrate ChatGPT into educational practices with integrity. Partnering with three Muhammadiyah Schools, the program trains 7-8 teachers from each institution. The training covers five key areas: (a) prompt engineering introduction, (b) building optimal prompts, (c) leveraging ChatGPT in teaching and learning, (d) prompt engineering for educational material creation, and (e) ethics of LLM usage in professional and academic settings. The effectiveness of this program is evaluated through pre-test and post-test questionnaires. Results indicate a significant improvement in prompt engineering proficiency, rising from 35.3% (pre-test) to 87.5% (post-test), and in the utilization of ChatGPT for learning support, increasing from 23.5% (pre-test) to 81.3% (post-test).

Manual inspection and remediation of guideline violations (UI design smells) is a knowledge-intensive, time-consuming, and context-related task that requires a high level of expertise. This paper proposes UISGPT, a novel end-to-end approach for automatically detecting user interface (UI) design smells and explaining each violation of specific design guidelines in natural language. To avoid hallucinations in large language models (LLMs) and achieve interpretable results, UISGPT uses few-shot learning and least-to-most prompting strategies to formalize design guidelines. To prevent the model from exceeding the input window size and for the enhancement of the logic in responses, UISGPT divides design smell detection into the following three subtasks: design guideline formalization, UI component information extraction, and guideline validation. The experimental results show that UISGPT performs effectively in automatically detecting design violations (F1 score of 0.729). In comparison to the latest LLM methods, the design smell reports generated by UISGPT have higher contextual consistency and user ratings. [ABSTRACT FROM AUTHOR]

In ethnographic research, data collected through surveys, interviews, or questionnaires in the fields of sociology and anthropology often appear in diverse forms and languages. Building a powerful database system to store and process such data, as well as making good and efficient queries, is very challenging. This paper extensively investigates modern database technology to find out what the best technologies to store these varied and heterogeneous datasets are. The study examines several database categories: traditional relational databases, the NoSQL family of key-value databases, graph databases, document databases, object-oriented databases and vector databases, crucial for the latest artificial intelligence solutions. The research proves that when it comes to field data, the NoSQL lineup is the most appropriate, especially document and graph databases. Simplicity and flexibility found in document databases and advanced ability to deal with complex queries and rich data relationships attainable with graph databases make these two types of NoSQL databases the ideal choice if a large amount of data has to be processed. Advancements in vector databases that embed custom metadata offer new possibilities for detailed analysis and retrieval. However, converting contents into vector data remains challenging, especially in regions with unique oral traditions and languages. Constructing such databases is labor-intensive and requires domain experts to define metadata and relationships, posing a significant burden for research teams with extensive data collections. To this end, this paper proposes using Generative AI (GenAI) to help in the data-transformation process, a recommendation that is supported by testing where GenAI has proven itself a strong supplement to document and graph databases. It also discusses two methods of vector database support that are currently viable, although each has drawbacks and benefits. [ABSTRACT FROM AUTHOR]

Entity Resolution (ER) is the problem of semi-automatically determining when two entities refer to the same underlying entity, with applications ranging from healthcare to e-commerce. Traditional ER solutions required considerable manual expertise, including domain-specific feature engineering, as well as identification and curation of training data. Recently released large language models (LLMs) provide an opportunity to make ER more seamless and domain-independent. Because of LLMs' pre-trained knowledge, the matching step in ER can be made easier by just prompting. However, it is also well known that LLMs can pose risks, that the quality of their outputs can depend on how prompts are engineered, and that the cost of using LLMs can be significant. Unfortunately, a systematic experimental study on the effects of different prompting methods and their respective cost for solving domain-specific entity matching using LLMs, like ChatGPT, has been lacking thus far. This paper aims to address this gap by conducting such a study. We consider some relatively simple and cost-efficient ER prompt engineering methods and apply them to perform product matching on two real-world datasets widely used in the community. We select two well-known e-commerce datasets and provide extensive experimental results to show that an LLM like GPT3.5 is viable for high-performing product matching and, interestingly, that more complicated and detailed (and hence, expensive) prompting methods do not necessarily outperform simpler approaches. We provide brief discussions on qualitative and error analysis, including a study of the inter-consistency of different prompting methods to determine whether they yield stable outputs. Finally, we consider some limitations of LLMs when used as a product matcher in potential real-world e-commerce applications. [ABSTRACT FROM AUTHOR]

"Are we asking the right questions?" seems cliché, but for ChatGPT, it is a pivotal tool to ensure the accuracy of responses. While ChatGPT-3.5's training on the vast database promises to revolutionize STEM education and research, this investigation shows the importance of precise communication and prompt engineering in guiding ChatGPT-3.5 toward reliable and accurate responses, particularly in chemistry. For instance, emphasizing context, clearly defining symbols, and focusing on field-specific instructions can dramatically improve its performance. Furthermore, avoiding open-ended prompts and strategically using repetition can further enhance its accuracy. The iterative prompt design, demonstrated through a series of adjustments, illustrates how seemingly minor refinements, such as substituting "least" for "lowest", profoundly impact the output. This study highlights the essential role of human oversight, including the construction of well-crafted prompts, in guarding reliable information and nurturing a productive "Human–AI" (HAI) partnership. [ABSTRACT FROM AUTHOR]