Search

BackgroundPatients find technology tools to be more approachable for seeking sensitive health-related information, such as reproductive health information. The inventive conversational ability of artificial intelligence (AI) chatbots, such as ChatGPT (OpenAI Inc), offers a potential means for patients to effectively locate answers to their health-related questions digitally.ObjectiveA pilot study was conducted to compare the novel ChatGPT with the existing Google Search technology for their ability to offer accurate, effective, and current information regarding proceeding action after missing a dose of oral contraceptive pill.MethodsA sequence of 11 questions, mimicking a patient inquiring about the action to take after missing a dose of an oral contraceptive pill, were input into ChatGPT as a cascade, given the conversational ability of ChatGPT. The questions were input into 4 different ChatGPT accounts, with the account holders being of various demographics, to evaluate potential differences and biases in the responses given to different account holders. The leading question, "what should I do if I missed a day of my oral contraception birth control?" alone was then input into Google Search, given its nonconversational nature. The results from the ChatGPT questions and the Google Search results for the leading question were evaluated on their readability, accuracy, and effective delivery of information.ResultsThe ChatGPT results were determined to be at an overall higher-grade reading level, with a longer reading duration, less accurate, less current, and with a less effective delivery of information. In contrast, the Google Search resulting answer box and snippets were at a lower-grade reading level, shorter reading duration, more current, able to reference the origin of the information (transparent), and provided the information in various formats in addition to text.ConclusionsChatGPT has room for improvement in accuracy, transparency, recency, and reliability before it can equitably be implemented into health care information delivery and provide the potential benefits it poses. However, AI may be used as a tool for providers to educate their patients in preferred, creative, and efficient ways, such as using AI to generate accessible short educational videos from health care provider-vetted information. Larger studies representing a diverse group of users are needed.

Over the last several decades, there has been an arms race to acquire credentials as higher education has shifted from an elitist system to mass education. From an individual perspective, given the higher education system and labor market conditions, it is rational to pursue advanced qualifications. However, whether the education system delivers improvements in human capital or is principally a signaling mechanism is questionable. Estimates of the proportion of labor market rewards due to signaling range as high as 80%, suggesting that education is not only expensive but inefficient. In an increasingly transactional environment in which education providers are highly motivated by financial considerations, this situation is only likely to be exacerbated by the rapid developments in artificial intelligence (AI). The use of AI has the potential to make learning more effective, but given that many students see credential acquisition as transactional, it may reduce both human capital and the value of the signaling effect. If the credibility of the credentials offered is further damaged, the higher education sector in its present form and scale may well be unsustainable. We examine the evidence on credential inflation, returns to education, and mismatch of graduates to jobs before analyzing how AI is likely to affect these trends. We then suggest possible responses of prospective students, education providers, and employers to the growing adoption of AI in both education and the workplace. We conclude that the current offerings of generalist degrees, as opposed to vocational qualifications, are not sustainable and that to survive, even in a downsized form, the sector must respond to this disruptive technology by changing both the nature of its offerings and its methods of ensuring that the credentials they offer reflect genuine student learning. [ABSTRACT FROM AUTHOR]

Human learning essentially involves embodied interactions with the material world. But our worlds now include increasing numbers of powerful and (apparently) disembodied generative artificial intelligence (AI). In what follows we ask how best to understand these new (somewhat 'alien', because of their disembodied nature) resources and how to incorporate them in our educational practices. We focus on methodologies that encourage exploration and embodied interactions with 'prepared' material environments, such as the carefully organized settings of Montessori education. Using the active inference framework, we approach our questions by thinking about human learning as epistemic foraging and prediction error minimization. We end by arguing that generative AI should figure naturally as new elements in prepared learning environments by facilitating sequences of precise prediction error enabling trajectories of self-correction. In these ways, we anticipate new synergies between (apparently) disembodied and (essentially) embodied forms of intelligence. This article is part of the theme issue 'Minds in movement: embodied cognition in the age of artificial intelligence'. [ABSTRACT FROM AUTHOR]

This article explores issue agenda-setting in Australia's 2023 Voice to Parliament referendum, analysing the dynamics of Yes and No campaigns in a diverse media ecosystem. We identify influential messages across this complex media environment using soft clustering of sentence embeddings from large language models (LLMs). Drawing on 3.3 million documents and over 10 million Voice specific sentences from mainstream and social media sources, we identify the narrative configurations of the campaigns, their audience size and engagement. Overall, the Yes campaign dominated with more diverse messaging and greater audience size and engagement than No. Yet, the No case prevailed. We find the narrower, mostly negative No campaign helped sustain the issue agenda both online and offline, forcing Yes to respond to it. The findings also challenge echo chamber theory, revealing most unique topics contained content from both #Yes and #No perspectives, indicating robust public engagement rather than isolated filter bubbles. [ABSTRACT FROM AUTHOR]

Humans excel at forming mental maps of their surroundings, equipping them to understand object relationships and navigate based on language queries. Our previous work SI Maps (Nanwani L, Agarwal A, Jain K, et al. Instance-level semantic maps for vision language navigation. In: 2023 32nd IEEE International Conference on Robot and Human Interactive Communication (RO-MAN). IEEE; 2023 Aug.) showed that having instance-level information and the semantic understanding of an environment helps significantly improve performance for language-guided tasks. We extend this instance-level approach to 3D while increasing the pipeline's robustness and improving quantitative and qualitative results. Our method leverages foundational models for object recognition, image segmentation, and feature extraction. We propose a representation that results in a 3D point cloud map with instance-level embeddings, which bring in the semantic understanding that natural language commands can query. Quantitatively, the work improves upon the success rate of language-guided tasks. At the same time, we qualitatively observe the ability to identify instances more clearly and leverage the foundational models and language and image-aligned embeddings to identify objects that, otherwise, a closed-set approach wouldn't be able to identify. Project Page - [ABSTRACT FROM AUTHOR]

Human Activity Recognition (HAR) is a rapidly evolving field with the potential to revolutionise how we monitor and understand human behaviour. This survey paper provides a comprehensive overview of the state-of-the-art in HAR, specifically focusing on recent techniques such as multimodal techniques, Deep Reinforcement Learning and large language models. It explores the diverse range of human activities and the sensor technologies employed for data collection. It then reviews novel algorithms used for Human Activity Recognition with emphasis on multimodality, Deep Reinforcement Learning and large language models. It gives an overview of multimodal datasets with physiological data. It also delves into the applications of HAR in healthcare. Additionally, the survey discusses the challenges and future directions in this exciting field, highlighting the need for continued research and development to fully realise the potential of HAR in various real-world applications. [ABSTRACT FROM AUTHOR]

This article presents a usability evaluation and comparison of generative AI applications through the analysis of user reviews from popular digital marketplaces, specifically Apple's App Store and Google Play. The study aims to bridge the research gap in real-world usability assessments of generative AI tools. A total of 11,549 reviews were extracted and analyzed from January to March 2024 for five generative AI apps: ChatGPT, Bing AI, Microsoft Copilot, Gemini AI, and Da Vinci AI. The dataset has been made publicly available, allowing for further analysis by other researchers. The evaluation follows ISO 9241 usability standards, focusing on effectiveness, efficiency, and user satisfaction. This study is believed to be the first usability evaluation for generative AI applications using user reviews across digital marketplaces. The results show that ChatGPT achieved the highest compound usability scores among Android and iOS users, with scores of 0.504 and 0.462, respectively. Conversely, Gemini AI scored the lowest among Android apps at 0.016, and Da Vinci AI had the lowest among iOS apps at 0.275. Satisfaction scores were critical in usability assessments, with ChatGPT obtaining the highest rates of 0.590 for Android and 0.565 for iOS, while Gemini AI had the lowest satisfaction rate at −0.138 for Android users. The findings revealed usability issues related to ease of use, functionality, and reliability in generative AI tools, providing valuable insights from user opinions and feedback. Based on the analysis, actionable recommendations were proposed to enhance the usability of generative AI tools, aiming to address identified usability issues and improve the overall user experience. This study contributes to a deeper understanding of user experiences and offers valuable guidance for enhancing the usability of generative AI applications. [ABSTRACT FROM AUTHOR]

The extraction of data from tables in PDF documents has been a longstanding challenge in the field of data processing and analysis. While traditional methods have been explored in depth, the rise of Large Language Models (LLMs) offers new possibilities. This article addresses the knowledge gaps regarding LLMs, specifically ChatGPT-4 and BARD, for extracting and interpreting data from financial tables in PDF format. This research is motivated by the real-world need to efficiently gather and analyze corporate financial information. The hypothesis is that LLMs—in this case, ChatGPT-4 and BARD—can accurately extract key financial data, such as balance sheets and income statements. The methodology involves selecting representative pages from 46 annual reports of large Swiss corporations listed in the SMI Expanded Index from 2022 and copy–pasting text from these into LLMs. Eight analytical questions were posed to the LLMs, and their responses were assessed for accuracy and for identifying potential error sources in data extraction. The findings revealed significant variance in the performance of ChatGPT-4 and another LLM, BARD, with ChatGPT-4 generally exhibiting superior accuracy. This research contributes to understanding the capabilities and limitations of LLMs in processing and interpreting complex financial data from corporate documents. [ABSTRACT FROM AUTHOR]

Traditional Chinese architecture boasts a unique style and profound cultural connotations. Accordingly, the related literary works attain value for international dissemination. The four-character structures in these works serve as concise expressions for describing architectural details and design concepts. However, due to their linguistic implicitness, grammatical structure diversity, and rich cultural images, their translation into English requires multidimensional shift, redundancy elimination, and the avoidance of cultural defaults. This research has developed an effective translation workflow that leverages the synergistic strengths of Large Language Models (LLMs) and the human translator. By strategically employing tailored methods and techniques, it addresses the challenges in the translation process. Analysis suggests: It is recommended that the technique of shift be employed to address the implicit content and complex grammatical structures in translating four-character structures in Chinese literary works on traditional architecture into English. Besides, the selective application of combination and omission can help deal with information redundancy. Furthermore, it is advisable to apply foreignization and a combined method of literal translation and paraphrasing in conveying cultural images. These approaches will, to a certain extent, convert the untranslatability of four-character structures into translatability, enhancing the dissemination of the essence of traditional Chinese architecture. [ABSTRACT FROM AUTHOR]

This study aims to evaluate the utilization and effectiveness of artificial intelligence (AI) applications in managing symptoms of anxiety and depression. The primary objectives are to identify current AI tools, analyze their practicality and efficacy, and assess their potential benefits and risks. A comprehensive literature review was conducted using databases such as ScienceDirect, Google Scholar, PubMed, and ResearchGate, focusing on publications from the last five years. The search utilized keywords including "artificial intelligence", "applications", "mental health", "anxiety", "LLMs" and "depression". Various AI tools, including chatbots, mobile applications, wearables, virtual reality settings, and large language models (LLMs), were examined and categorized based on their functions in mental health care. The findings indicate that AI applications, including LLMs, show significant promise in symptom management, offering accessible and personalized interventions that can complement traditional mental health treatments. Tools such as AI-driven chatbots, mobile apps, and LLMs have demonstrated efficacy in reducing symptoms of anxiety and depression, improving user engagement and mental health outcomes. LLMs, in particular, have shown potential in enhancing therapeutic chatbots, diagnostic tools, and personalized treatment plans by providing immediate support and resources, thus reducing the workload on mental health professionals. However, limitations include concerns over data privacy, the potential for overreliance on technology, and the need for human oversight to ensure comprehensive care. Ethical considerations, such as data security and the balance between AI and human interaction, were also addressed. The study concludes that while AI, including LLMs, has the potential to significantly aid mental health care, it should be used as a complement to, rather than a replacement for, human therapists. Future research should focus on enhancing data security measures, integrating AI tools with traditional therapeutic methods, and exploring the long-term effects of AI interventions on mental health. Further investigation is also needed to evaluate the effectiveness of AI applications across diverse populations and settings. [ABSTRACT FROM AUTHOR]

Dementia is primarily caused by neurodegenerative diseases like Alzheimer's disease (AD). It affects millions worldwide, making detection and monitoring crucial. This study focuses on the detection of dementia from speech transcripts of controls and dementia groups. We propose encoding in-text pauses and filler words (e.g., "uh" and "um") in text-based language models and thoroughly evaluating their impact on performance (e.g., accuracy). Additionally, we suggest using contrastive learning to improve performance in a multi-task framework. Our results demonstrate the effectiveness of our approaches in enhancing the model's performance, achieving 87% accuracy and an 86% f1-score. Compared to the state of the art, our approach has similar performance despite having significantly fewer parameters. This highlights the importance of pause and filler word encoding on the detection of dementia. [ABSTRACT FROM AUTHOR]

This paper compares two approaches to support Business Process Analysis (BPA) for the construction of a Business Process Knowledge Base (BPKB). The methodology is based on the BPA Canvas metamodel, which starts from the preliminary output of the business analysis (an interview). We focus on the extraction of key elements from the text to build the BPKBcore. We experiment with approaches based on Natural Language Processing (NLP) and Large Language Models (LLMs), using a running example to compare the outcomes with manual annotations. The experiment shows that the LLM-based approach yields better performance, especially with enriched prompts. [ABSTRACT FROM AUTHOR]

Current stance detection methods employ topic-aligned data, resulting in many unexplored topics due to insufficient training samples. Large Language Models (LLMs) pre-trained on a vast amount of web data offer a viable solution when training data is unavailable. This work introduces Tweets2Stance - T2S, an unsupervised stance detection framework based on zero-shot classification, i.e. leveraging an LLM pre-trained on Natural Language Inference tasks. T2S detects a five-valued user's stance on social-political statements by analyzing their X (Twitter) timeline. The Ground Truth of a user's stance is obtained from Voting Advice Applications (VAAs). Through comprehensive experiments, a T2S's optimal setting was identified for each election. Linguistic limitations related to the language model are further addressed by integrating state-of-the-art LLMs like GPT-4 and Mixtral into the T2S framework. The T2S framework's generalization potential is demonstrated by measuring its performance (F1 and MAE scores) across nine datasets. These datasets were built by collecting tweets from competing parties' Twitter accounts in nine political elections held in different countries from 2019 to 2021. The results, in terms of F1 and MAE scores, outperformed all baselines and approached the best scores for each election. This showcases the ability of T2S, particularly when combined with state-of-the-art LLMs, to generalize across different cultural-political contexts. [ABSTRACT FROM AUTHOR]

The flight arrival scheduling problem is one of the critical tasks in air traffic operations, aiming to ensure that the flight arrive in the correct sequence safely. Existing methods primarily focus on the terminal area and often overlook the presence of training flight at the airport. Due to the limited generalization of traditional methods and varying control practices at different airports, training flight at airports still rely on manual control for arrival sorting. To effectively address these issues, we propose a novel method for slot allocation that leverages the strong reasoning capabilities and generalization potential of large language models (LLMs). Our method conceptualizes the dynamic scheduling problem for training flight as a language modeling problem, a perspective not previously explored. Specifically, we represent the allocator's inputs and outputs as language tokens, utilizing LLMs to generate conflict-free results based on a language description of requested landing information and assigned training flight information. Additionally, we employ a reset strategy to create a small dataset for scenario-specific samples, enabling LLMs to quickly learn allocation schemes from the dataset. We demonstrated the capability of LLMs in addressing time conflicts by evaluating metrics such as answer accuracy, conflict rate, and total delay time (without the wrong answer). These findings underscore the feasibility of employing LLMs in the field of air traffic control. [ABSTRACT FROM AUTHOR]

Most current methods use spatial–temporal graph neural networks (STGNNs) to analyze complex spatial–temporal information from traffic data collected from hundreds of sensors. STGNNs combine graph neural networks (GNNs) and sequence models to create hybrid structures that allow for the two networks to collaborate. However, this collaboration has made the model increasingly complex. This study proposes a framework that relies solely on original Transformer architecture and carefully designs embeddings to efficiently extract spatial–temporal dependencies in traffic flow. Additionally, we used pre-trained language models to enhance forecasting performance. We compared our new framework with current state-of-the-art STGNNs and Transformer-based models using four real-world traffic datasets: PEMS04, PEMS08, METR-LA, and PEMS-BAY. The experimental results demonstrate that our framework outperforms the other models in most metrics. [ABSTRACT FROM AUTHOR]

Large Language Models (LLMs) are transformer‐based neural networks with billions of parameters trained on very large text corpora from diverse sources. LLMs have the potential to improve healthcare due to their capability to parse complex concepts and generate context‐based responses. The interest in LLMs has not spared digestive disease academics, who have mainly investigated foundational LLM accuracy, which ranges from 25% to 90% and is influenced by the lack of standardized rules to report methodologies and results for LLM‐oriented research. In addition, a critical issue is the absence of a universally accepted definition of accuracy, varying from binary to scalar interpretations, often tied to grader expertise without reference to clinical guidelines. We address strategies and challenges to increase accuracy. In particular, LLMs can be infused with domain knowledge using Retrieval Augmented Generation (RAG) or Supervised Fine‐Tuning (SFT) with reinforcement learning from human feedback (RLHF). RAG faces challenges with in‐context window limits and accurate information retrieval from the provided context. SFT, a deeper adaptation method, is computationally demanding and requires specialized knowledge. LLMs may increase patient quality of care across the field of digestive diseases, where physicians are often engaged in screening, treatment and surveillance for a broad range of pathologies for which in‐context learning or SFT with RLHF could improve clinical decision‐making and patient outcomes. However, despite their potential, the safe deployment of LLMs in healthcare still needs to overcome hurdles in accuracy, suggesting a need for strategies that integrate human feedback with advanced model training. [ABSTRACT FROM AUTHOR]

Large language models (LLMs) like ChatGPT and Bard have the potential to greatly benefit healthcare, including the field of uveitis care. LLMs can provide accessible advice for patients, helping them make decisions about when to seek medical attention or escalate their treatment. They can also assist in the diagnosis of uveitis, although more research specific to uveitis is needed. LLMs can improve the consultation experience by engaging with patients and providing empathetic responses. Additionally, they can aid in medication management and streamline administrative processes. LLMs have the potential to accelerate research in uveitis by automating tasks such as data analysis and identifying potential drug targets. However, there are ethical considerations to address, including patient autonomy, bias, transparency, and accountability. Efforts should be made to ensure equity and accessibility in the implementation of LLMs, and regulatory frameworks should be developed to ensure responsible use. The future directions of LLMs in uveitis care include integrating them with visual and auditory processing and training them in real-time. While LLMs show promise, more research is needed to develop them with reliability and replicability. [Extracted from the article]

The profound digitization of public administration over recent decades has not eliminated information exchange via paper or electronic documents and certificates. We argue that a paradigm shift from document-centric to data-centric public service provision is needed and is feasible today with the exploitation of emerging technologies. We explore frameworks, architectures, benefits, and challenges in transforming document-centric administration processes into integrated, granular data exchange. A conceptual architecture for public service provision is proposed to extract preconditions from legislation, map the needed evidence to the service requirements, standardize evidence types, and integrate authoritative data sources. While promoting efficiency, privacy, and innovation, this shift faces technical and organizational challenges as the analysis of the "National Registry of Administrative Public Services" in Greece reveals. Further research on aligning policies, upholding trust, and coordinating institutional processes is warranted. [ABSTRACT FROM AUTHOR]

The cost landscape in advanced technology systems is shifting dramatically. Traditionally, hardware costs took the spotlight, but now, programming and debugging complexities are gaining prominence. This paper explores this shift and its implications, focusing on reducing the cost of programming complex robot behaviors, using the latest innovations from the Generative AI field, such as large language models (LLMs). We leverage finite state machines (FSMs) and LLMs to streamline robot programming while ensuring functionality. The paper addresses LLM challenges related to content quality, emphasizing a two-fold approach using predefined software blocks and a Supervisory LLM. [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.)

The rapid increase in scientific publications has made it challenging to keep up with the latest advancements. Conducting systematic reviews using traditional methods is both time-consuming and difficult. To address this, new review formats like rapid and scoping reviews have been introduced, reflecting an urgent need for efficient information retrieval. This challenge extends beyond academia to many organizations where numerous documents must be reviewed in relation to specific user queries. This paper focuses on improving document ranking to enhance the retrieval of relevant articles, thereby reducing the time and effort required by researchers. By applying a range of natural language processing (NLP) techniques, including rule-based matching, statistical text analysis, word embeddings, and transformer- and LLM-based approaches like Mistral LLM, we assess the article's similarities to user-specific inputs and prioritize them according to relevance. We propose a novel methodology, Weighted Semantic Matching (WSM) + MiniLM, combining the strengths of the different methodologies. For validation, we employ global metrics such as precision at K, recall at K, average rank, median rank, and pairwise comparison metrics, including higher rank count, average rank difference, and median rank difference. Our proposed algorithm achieves optimal performance, with an average recall at 1000 of 95% and an average median rank of 185 for selected articles across the five datasets evaluated. These findings give promising results in pinpointing the relevant articles and reducing the manual work. [ABSTRACT FROM AUTHOR]

Synthetic data are increasingly being recognized for their potential to address serious real-world challenges in various domains. They provide innovative solutions to combat the data scarcity, privacy concerns, and algorithmic biases commonly used in machine learning applications. Synthetic data preserve all underlying patterns and behaviors of the original dataset while altering the actual content. The methods proposed in the literature to generate synthetic data vary from large language models (LLMs), which are pre-trained on gigantic datasets, to generative adversarial networks (GANs) and variational autoencoders (VAEs). This study provides a systematic review of the various techniques proposed in the literature that can be used to generate synthetic data to identify their limitations and suggest potential future research areas. The findings indicate that while these technologies generate synthetic data of specific data types, they still have some drawbacks, such as computational requirements, training stability, and privacy-preserving measures which limit their real-world usability. Addressing these issues will facilitate the broader adoption of synthetic data generation techniques across various disciplines, thereby advancing machine learning and data-driven solutions. [ABSTRACT FROM AUTHOR]

The concept of imitation is both ubiquitous and curiously under-analysed in theoretical discussions about the cognitive powers and capacities of machines, and in particular—for what is the focus of this paper—the cognitive capacities of large language models (LLMs). The question whether LLMs understand what they say and what is said to them, for instance, is a disputed one, and it is striking to see this concept of imitation being mobilised here for sometimes contradictory purposes. After illustrating and discussing how this concept is being used in various ways in the context of conversational systems, I draw a sketch of the different associations that the term ‘imitation’ conveys and distinguish two main senses of the notion. The first one is what I call the ‘imitative behaviour’ and the second is what I call the ‘status of imitation’. I then highlight and untangle some conceptual difficulties with these two senses and conclude that neither of these applies to LLMs. Finally, I introduce an appropriate description that I call ‘imitation manufacturing’. All this ultimately helps me to explore a radical negative answer to the question of machine understanding. [ABSTRACT FROM AUTHOR]

Abstract Software Defect Detection (SDD) has always been critical to the development life cycle. A stable defect detection system can not only alleviate the workload of software testers but also enhance the overall efficiency of software development. Researchers have recently proposed various artificial intelligence-based SDD methods and achieved significant advancements. However, these methods still exhibit limitations in terms of reliability and usability. Therefore, we introduce MSDD-(IA)3, a novel framework leveraging the pre-trained CodeT5+ and (IA)3 for parameter-efficient multi-classification SDD. This framework constructs a detection model based on pre-trained CodeT5+ to generate code representations while capturing defect-prone features. Considering the high overhead of pre-trained LLMs, we injects (IA)3 vectors into specific layers, where only these injected parameters are updated to reduce the training cost. Furthermore, leveraging the properties of the pre-trained CodeT5+, we design a novel feature sequence that enriches the input data through the combination of source code with Natural Language (NL)-based expert metrics. Our experimental results on 64K real-world Python snippets show that MSDD-(IA)3 demonstrates superior performance compared to state-of-the-art SDD methods, including PM2-CNN, in terms of F1-weighted, Recall-weighted, Precision-weighted, and Matthews Correlation Coefficient. Notably, the training parameters of MSDD-(IA)3 are only 0.04% of those of the original CodeT5+. Our experimental data and code can be available at ( https://gitee.com/wxyzjp123/msdd-ia3/ ).

This report summarizes APE 2024 (Academic Publishing in Europe, 9–10 January 2024, Berlin, Germany), the 19th edition of the yearly conference bringing together stakeholders within the realm of scholarly publishing. This year’s conference, moderated by Brill’s Chief Publishing Officer Jasmin Lange, was themed ‘Keep the Conversation Going,’ and highlighted topics such as publishers contributing to the SDGs, research integrity, the pros and cons of AI, and open science. [ABSTRACT FROM AUTHOR]

Pharmacovigilance plays a crucial role in ensuring the safety of pharmaceutical products. It involves the systematic monitoring of adverse events and the detection of potential safety concerns related to drugs. Manual literature screening for pharmacovigilance related articles is a labor-intensive and time-consuming task, requiring streamlined solutions to cope with the continuous growth of literature. The primary objective of this study is to assess the performance of Large Language Models (LLMs) in automating literature screening for pharmacovigilance, aiming to enhance the process by identifying relevant articles more effectively. This study represents a novel application of LLMs including OpenAI's GPT-3.5, GPT-4, and Anthropic's Claude2, in the field of pharmacovigilance, evaluating their ability to categorize medical publications as relevant or irrelevant for safety signal reviews. Our analysis encompassed N-shot learning, chain-of-thought reasoning, and evaluating metrics, with a focus on factors impacting accuracy. The findings highlight the promising potential of LLMs in literature screening, achieving a reproducibility of 93%, sensitivity of 97%, and specificity of 67% showcasing notable strengths in terms of reproducibility and sensitivity, although with moderate specificity. Notably, performance improved when models were provided examples consisting of abstracts, labels, and corresponding reasoning explanations. Moreover, our exploration identified several potential contributing factors influencing prediction outcomes. These factors encompassed the choice of key words and prompts, the balance of the examples, and variations in reasoning explanations. By configuring advanced LLMs for efficient screening of extensive literature databases, this study underscores the transformative potential of these models in drug safety monitoring. Furthermore, these insights gained from this study can inform the development of automated systems for pharmacovigilance, contributing to the ongoing efforts to ensure the safety and efficacy of pharmacovigilance products. [ABSTRACT FROM AUTHOR]

Background: With their unmatched ability to interpret and engage with human language and context, large language models (LLMs) hint at the potential to bridge AI and human cognitive processes. This review explores the current application of LLMs, such as ChatGPT, in the field of psychiatry. Methods: We followed PRISMA guidelines and searched through PubMed, Embase, Web of Science, and Scopus, up until March 2024. Results: From 771 retrieved articles, we included 16 that directly examine LLMs' use in psychiatry. LLMs, particularly ChatGPT and GPT-4, showed diverse applications in clinical reasoning, social media, and education within psychiatry. They can assist in diagnosing mental health issues, managing depression, evaluating suicide risk, and supporting education in the field. However, our review also points out their limitations, such as difficulties with complex cases and potential underestimation of suicide risks. Conclusion: Early research in psychiatry reveals LLMs' versatile applications, from diagnostic support to educational roles. Given the rapid pace of advancement, future investigations are poised to explore the extent to which these models might redefine traditional roles in mental health care. [ABSTRACT FROM AUTHOR]

Phishing emails exploit human vulnerabilities to illicitly obtain sensitive information, representing a critical research focus in cybersecurity. This study explores the effectiveness of artificial intelligence (AI), specifically Large Language Models (LLMs), in detecting phishing emails. Evaluating LLM-based models, including ChatGPT-4 and Gemini, the study directly tests them on a mixed dataset of sanitized phishing emails and non-phishing emails using a defined set of phishing indicators and measures. The findings contribute to understanding the practical application of AI in detecting phishing attempts, advancing discourse on AI's role in cybersecurity. [ABSTRACT FROM AUTHOR]

In the context of low-resource languages, the Algerian dialect (AD) faces challenges due to the absence of annotated corpora, hindering its effective processing, notably in Machine Learning (ML) applications reliant on corpora for training and assessment. This study outlines the development process of a specialized corpus for Fake News (FN) detection and sentiment analysis (SA) in AD called FASSILA. This corpus comprises 10,087 sentences, encompassing over 19,497 unique words in AD, addresses the language's significant lack of linguistic resources, and covers seven distinct domains. We propose an FN detection and SA annotation scheme detailing the data collection, cleaning, and labeling. The remarkable Inter-Annotator Agreement indicates that the annotation scheme produces high-quality and consistent annotations. Subsequent classification experiments using BERT-based and ML models are presented, demonstrating promising results and highlighting avenues for further research. The dataset is currently freely available to facilitate future advancements in the field. [ABSTRACT FROM AUTHOR]

This work investigates the processing behavior of large language models (LLMs) in sentences involving ambiguous relative clauses (RCs). We are particularly interested in unravelling attachment preferences of LLMs in disambiguating RCs (complementizer phrases CPs modifying a genitival phrase), which are either semantically (context-biased) or syntactically (structure-biased) associated to one of the preceding NP referents. A low interpretation of the RC occurs when it is joined to the local NP (low attachment). A high interpretation is provided when the RC modifies the distant NP (high attachment). We create a small dataset of parallel low- and high-attachment sentences. We use zero-shot prompting to evaluate a set of LLMs based on insights from psycholinguistic experiments. Our results show variability in the performance of some models that favor low attachment (semantically-related meanings in the CP) while other models can resolve ambiguity by choosing high-attachment (structure-biased CPs). The findings are discussed in light of directing future experimental studies to consider a comparative paradigm encompassing both multi-modal LLMs and human subjects. [ABSTRACT FROM AUTHOR]

Retrieval-augmented generation (RAG) adds a simple but powerful feature to chatbots, the ability to upload files just-in-time. Chatbots are trained on large quantities of public data. The ability to upload files just-in-time makes it possible to reduce hallucinations by filling in gaps in the knowledge base that go beyond the public training data such as private data and recent events. For example, in a customer service scenario, with RAG, we can upload your private bill and then the bot can discuss questions about your bill as opposed to generic FAQ questions about bills in general. This tutorial will show how to upload files and generate responses to prompts; see https://github.com/kwchurch/RAG for multiple solutions based on tools from OpenAI, LangChain, HuggingFace transformers and VecML. [ABSTRACT FROM AUTHOR]

Purpose: Lifelong learning has become one of the most interesting areas of research. Hence, the current study was aimed at developing and validating a tool that helps to study how well people working in higher education institutions are engaged in lifelong learning. Design/methodology/approach: A review of theories in the literature and experts' consultation were used to develop a pool of items and validate the self-assessment instrument for measuring lifelong learning. The study employed factor analytic methodologies such as principal component analysis, varimax rotation and exploratory factor analyses. Findings: The study yielded a reliable and valid lifelong learning measurement scale made up of 18 items and four underlying factors that are theoretically supported. Originality/value: The significant information is that, the current study aimed at developing a tool that could help to measure the engagement in lifelong learning of higher education institutions workers. The study found this tool to be important because lifelong learning is considered essential for personal and professional growth, and having a sound way to measure it can help individuals and organizations identify areas for improvement. [ABSTRACT FROM AUTHOR]

Annotation tools serve a critical role in the generation of datasets that fuel machine learning applications. With the advent of Foundation Models, particularly those based on Transformer architectures and expansive language models, the capacity for training on comprehensive, multimodal datasets has been substantially enhanced. This not only facilitates robust generalization across diverse data categories and knowledge domains but also necessitates a novel form of annotation—prompt engineering—for qualitative model fine-tuning. This advancement creates new avenues for machine intelligence to more precisely identify, forecast, and replicate human behavior, addressing historical limitations that contribute to algorithmic inequities. Nevertheless, the voluminous and intricate nature of the data essential for training multimodal models poses significant engineering challenges, particularly with regard to bias. No consensus has yet emerged on optimal procedures for conducting this annotation work in a manner that is ethically responsible, secure, and efficient. This historical literature review traces advancements in these technologies from 2018 onward, underscores significant contributions, and identifies existing knowledge gaps and avenues for future research pertinent to the development of Transformer-based multimodal Foundation Models. An initial survey of over 724 articles yielded 156 studies that met the criteria for historical analysis; these were further narrowed down to 46 key papers spanning the years 2018–2022. The review offers valuable perspectives on the evolution of best practices, pinpoints current knowledge deficiencies, and suggests potential directions for future research. The paper includes six figures and delves into the transformation of research landscapes in the realm of machine-assisted behavioral annotation, focusing on critical issues such as bias. [ABSTRACT FROM AUTHOR]

As modern technologies, particularly home assistant devices and sensors, become more integrated into our daily lives, they are also making their way into the domain of energy management within our homes. Homeowners, now acting as prosumers, have access to detailed information at 15-min or even 5-min intervals, including weather forecasts, outputs from renewable energy source (RES)-based systems, appliance schedules and the current energy balance, which details any deficits or surpluses along with their quantities and the predicted prices on the local energy market (LEM). The goal for these prosumers is to reduce costs while ensuring their home's comfort levels are maintained. However, given the complexity and the rapid decision-making required in managing this information, the need for a supportive system is evident. This is particularly true given the routine nature of these decisions, highlighting the potential for a system that provides personalized recommendations to optimize energy consumption, whether that involves adjusting the load or engaging in transactions with the LEM. In this context, we propose a recommendation system powered by large language models (LLMs), Scikit-llm and zero-shot classifiers, designed to evaluate specific scenarios and offer tailored advice for prosumers based on the available data at any given moment. Two scenarios for a prosumer of 5.9 kW are assessed using candidate labels, such as Decrease, Increase, Sell and Buy. A comparison with a content-based filtering system is provided considering the performance metrics that are relevant for prosumers. [ABSTRACT FROM AUTHOR]

The remarkable strides in artificial intelligence (AI), exemplified by ChatGPT, have unveiled a wealth of opportunities and challenges in assessment. Applying cutting‐edge large language models (LLMs) and generative AI to assessment holds great promise in boosting efficiency, mitigating bias, and facilitating customized evaluations. Conversely, these innovations raise significant concerns regarding validity, reliability, transparency, fairness, equity, and test security, necessitating careful thinking when applying them in assessments. In this article, we discuss the impacts and implications of LLMs and generative AI on critical dimensions of assessment with example use cases and call for a community effort to equip assessment professionals with the needed AI literacy to harness the potential effectively. [ABSTRACT FROM AUTHOR]

Recent developments in large language models (LLMs) have opened new avenues for the real estate industry. These models not only understand language but also function as intelligent agents, engaging with investors through open-ended conversations and influencing their decision-making. Utilizing unstructured data from a professional Danish real estate website, we developed a real estate AI agent in both English and Danish using LangChain and Pinecone. Through testing and evaluation, our agent has demonstrated superior professional and concise outputs compared to other LLMs like Doubao and ChatGPT 4 and shown excellent performance and effectiveness. Our work serves as a reference for AI in real estate investment-related research and proposes new solutions to the "unprofessional foundation " and " expensive consulting fee" problems encountered by ordinary investors in their investment decisions. [ABSTRACT FROM AUTHOR]

Recently, there has been considerable interest in large language models: machine learning systems which produce human-like text and dialogue. Applications of these systems have been plagued by persistent inaccuracies in their output; these are often called “AI hallucinations”. We argue that these falsehoods, and the overall activity of large language models, is better understood as bullshit in the sense explored by Frankfurt (On Bullshit, Princeton, 2005): the models are in an important way indifferent to the truth of their outputs. We distinguish two ways in which the models can be said to be bullshitters, and argue that they clearly meet at least one of these definitions. We further argue that describing AI misrepresentations as bullshit is both a more useful and more accurate way of predicting and discussing the behaviour of these systems. [ABSTRACT FROM AUTHOR]