Search

This paper introduces a novel approach to create a high-resolution "map" for physics learning: an "atomic" learning objectives (LOs) system designed to capture detailed cognitive processes and concepts required for problem solving in a college-level introductory physics course. Our method leverages Large Language Models (LLMs) for automated labeling of physics questions and introduces a comprehensive set of metrics to evaluate the quality of the labeling outcomes. The atomic LO system, covering nine chapters of an introductory physics course, uses a "subject-verb-object'' structure to represent specific cognitive processes. We apply this system to 131 questions from expert-curated question banks and the OpenStax University Physics textbook. Each question is labeled with 1-8 atomic LOs across three chapters. Through extensive experiments using various prompting strategies and LLMs, we compare automated LOs labeling results against human expert labeling. Our analysis reveals both the strengths and limitations of LLMs, providing insight into LLMs reasoning processes for labeling LOs and identifying areas for improvement in LOs system design. Our work contributes to the field of learning analytics by proposing a more granular approach to mapping learning objectives with questions. Our findings have significant implications for the development of intelligent tutoring systems and personalized learning pathways in STEM education, paving the way for more effective "learning GPS'' systems., Comment: The paper is accepted to LAK'2025

Accurately modeling student cognition is crucial for developing effective AI-driven educational technologies. A key challenge is creating realistic student models that satisfy two essential properties: (1) accurately replicating specific misconceptions, and (2) correctly solving problems where these misconceptions are not applicable. This dual requirement reflects the complex nature of student understanding, where misconceptions coexist with correct knowledge. This paper investigates whether Large Language Models (LLMs) can be instruction-tuned to meet this dual requirement and effectively simulate student thinking in algebra. We introduce MalAlgoPy, a novel Python library that generates datasets reflecting authentic student solution patterns through a graph-based representation of algebraic problem-solving. Utilizing MalAlgoPy, we define and examine Cognitive Student Models (CSMs) - LLMs instruction tuned to faithfully emulate realistic student behavior. Our findings reveal that LLMs trained on misconception examples can efficiently learn to replicate errors. However, the training diminishes the model's ability to solve problems correctly, particularly for problem types where the misconceptions are not applicable, thus failing to satisfy second property of CSMs. We demonstrate that by carefully calibrating the ratio of correct to misconception examples in the training data - sometimes as low as 0.25 - it is possible to develop CSMs that satisfy both properties. Our insights enhance our understanding of AI-based student models and pave the way for effective adaptive learning systems.

This paper introduces MalAlgoQA, a novel dataset designed to evaluate the counterfactual reasoning capabilities of Large Language Models (LLMs) through a pedagogical approach. The dataset comprises mathematics and reading comprehension questions, each accompanied by four answer choices and their corresponding rationales. At the heart of MalAlgoQA are ``malgorithms'' - rationales behind incorrect answer choices that represent flawed yet logically coherent reasoning paths. These malgorithms serve as counterfactual scenarios, allowing us to assess an LLM's ability to identify and analyze flawed reasoning patterns. We propose the Malgorithm Identification task, where LLMs are assessed based on their ability to identify corresponding malgorithm given an incorrect answer choice. To evaluate the model performance, we introduce two metrics: Algorithm Identification Accuracy (AIA) for correct answer rationale identification, and Malgorithm Identification Accuracy (MIA) for incorrect answer rationale identification. Our experiments reveal that state-of-the-art LLMs exhibit significant performance drops in MIA compared to AIA, highlighting the challenges in counterfactual reasoning. Surprisingly, we find that the chain-of-thought prompting technique not only fails to consistently enhance MIA but can sometimes lead to underperformance compared to simple prompting. These findings have important implications for developing LLMs with improved counterfactual reasoning, particularly relevant for AI-powered tutoring systems, where identifying and addressing student misconceptions is essential. MalAlgoQA dataset is available \href{https://github.com/luffycodes/MalAlgoQA-Dataset}{here}., Comment: Accepted at EMNLP 2024 Findings Track

We introduce Many-Shot Regurgitation (MSR) prompting, a new black-box membership inference attack framework for examining verbatim content reproduction in large language models (LLMs). MSR prompting involves dividing the input text into multiple segments and creating a single prompt that includes a series of faux conversation rounds between a user and a language model to elicit verbatim regurgitation. We apply MSR prompting to diverse text sources, including Wikipedia articles and open educational resources (OER) textbooks, which provide high-quality, factual content and are continuously updated over time. For each source, we curate two dataset types: one that LLMs were likely exposed to during training ($D_{\rm pre}$) and another consisting of documents published after the models' training cutoff dates ($D_{\rm post}$). To quantify the occurrence of verbatim matches, we employ the Longest Common Substring algorithm and count the frequency of matches at different length thresholds. We then use statistical measures such as Cliff's delta, Kolmogorov-Smirnov (KS) distance, and Kruskal-Wallis H test to determine whether the distribution of verbatim matches differs significantly between $D_{\rm pre}$ and $D_{\rm post}$. Our findings reveal a striking difference in the distribution of verbatim matches between $D_{\rm pre}$ and $D_{\rm post}$, with the frequency of verbatim reproduction being significantly higher when LLMs (e.g. GPT models and LLaMAs) are prompted with text from datasets they were likely trained on. For instance, when using GPT-3.5 on Wikipedia articles, we observe a substantial effect size (Cliff's delta $= -0.984$) and a large KS distance ($0.875$) between the distributions of $D_{\rm pre}$ and $D_{\rm post}$. Our results provide compelling evidence that LLMs are more prone to reproducing verbatim content when the input text is likely sourced from their training data.

The pursuit of personalized education has led to the integration of Large Language Models (LLMs) in developing intelligent tutoring systems. To better understand and adapt to individual student needs, including their misconceptions, LLMs need to be trained on extensive datasets of student-tutor dialogues. Our research uncovers a fundamental challenge in this approach: the ``Student Data Paradox.'' This paradox emerges when LLMs, trained on student data to understand learner behavior, inadvertently compromise their own factual knowledge and reasoning abilities. We investigate this paradox by training state-of-the-art language models on student-tutor dialogue datasets and evaluating their performance across multiple benchmarks. These benchmarks assess various aspects of language model capabilities, including reasoning, truthfulness, and common sense understanding. Our findings reveal significant declines in the models' performance across these diverse benchmarks, indicating a broad impact on their capabilities when trained to model student behavior. Our research makes two primary contributions: (1) empirical demonstration of the Student Data Paradox through quantitative analysis of model performance, and (2) introduction of ``hallucination tokens'' as a mitigation strategy. These tokens, while improving performance, highlight the persistent challenge of balancing accurate student behavior modeling with maintaining the LLM's integrity as an educational tool. This study emphasizes the need for innovative solutions to reconcile the conflicting goals of faithfully understanding diverse student cognition while preserving the model's ability to provide accurate information and guidance., Comment: Accepted at EMNLP 2024 Findings Track

We introduce a new area of study in the field of educational Natural Language Processing: Automated Long Answer Grading (ALAG). Distinguishing itself from Automated Short Answer Grading (ASAG) and Automated Essay Grading (AEG), ALAG presents unique challenges due to the complexity and multifaceted nature of fact-based long answers. To study ALAG, we introduce RiceChem, a dataset derived from a college chemistry course, featuring real student responses to long-answer questions with an average word count notably higher than typical ASAG datasets. We propose a novel approach to ALAG by formulating it as a rubric entailment problem, employing natural language inference models to verify whether each criterion, represented by a rubric item, is addressed in the student's response. This formulation enables the effective use of MNLI for transfer learning, significantly improving the performance of models on the RiceChem dataset. We demonstrate the importance of rubric-based formulation in ALAG, showcasing its superiority over traditional score-based approaches in capturing the nuances of student responses. We also investigate the performance of models in cold start scenarios, providing valuable insights into the practical deployment considerations in educational settings. Lastly, we benchmark state-of-the-art open-sourced Large Language Models (LLMs) on RiceChem and compare their results to GPT models, highlighting the increased complexity of ALAG compared to ASAG. Despite leveraging the benefits of a rubric-based approach and transfer learning from MNLI, the lower performance of LLMs on RiceChem underscores the significant difficulty posed by the ALAG task. With this work, we offer a fresh perspective on grading long, fact-based answers and introduce a new dataset to stimulate further research in this important area. Code: \url{https://github.com/luffycodes/Automated-Long-Answer-Grading}.

In this paper, we introduce "Marking", a novel grading task that enhances automated grading systems by performing an in-depth analysis of student responses and providing students with visual highlights. Unlike traditional systems that provide binary scores, "marking" identifies and categorizes segments of the student response as correct, incorrect, or irrelevant and detects omissions from gold answers. We introduce a new dataset meticulously curated by Subject Matter Experts specifically for this task. We frame "Marking" as an extension of the Natural Language Inference (NLI) task, which is extensively explored in the field of Natural Language Processing. The gold answer and the student response play the roles of premise and hypothesis in NLI, respectively. We subsequently train language models to identify entailment, contradiction, and neutrality from student response, akin to NLI, and with the added dimension of identifying omissions from gold answers. Our experimental setup involves the use of transformer models, specifically BERT and RoBERTa, and an intelligent training step using the e-SNLI dataset. We present extensive baseline results highlighting the complexity of the "Marking" task, which sets a clear trajectory for the upcoming study. Our work not only opens up new avenues for research in AI-powered educational assessment tools, but also provides a valuable benchmark for the AI in education community to engage with and improve upon in the future. The code and dataset can be found at https://github.com/luffycodes/marking.

A three-level quantum system having two energy gaps presents a nontrivial working medium for a quantum heat engine. Our focus lies in understanding the constraints on the ability to modulate these gaps relative to the changes in probability distributions at the two given heat reservoirs. It is seen that an Otto engine in the quasistatic limit is feasible if at least one energy gap shrinks during the first quantum adiabatic stage. We analyze operating conditions under different variations of the gaps, revealing that a definite majorization relation between the hot and cold distributions serves as a sufficient criterion for the engine when both gaps are shrinking. Further, Otto efficiency is enhanced in case majorization holds. On the other hand, majorization becomes a necessary condition when only one of the gaps is shrinking. In the special case where one gap remains fixed, majorization is both necessary and sufficient for engine operation. For an $n$-level system, we note that a well defined change in energy gaps aligns with the majorization relation, thus characterizing the operation of the engine., Comment: 24 pages, 6 figures

Large Language Models (LLMs), when used in educational settings without pedagogical fine-tuning, often provide immediate answers rather than guiding students through the problem-solving process. This approach falls short of pedagogically best practices and limits their effectiveness as educational tools. We term the objective of training LLMs to emulate effective teaching strategies as `pedagogical alignment.' In this paper, we investigate Learning from Human Preferences (LHP) algorithms to achieve this alignment objective. A key challenge in this process is the scarcity of high-quality preference datasets to guide the alignment. To address this, we propose a novel approach for constructing a large-scale dataset using synthetic data generation techniques, eliminating the need for time-consuming and costly manual annotation. Leveraging this dataset, our experiments with Llama and Mistral models demonstrate that LHP methods outperform standard supervised fine-tuning (SFT), improving pedagogical alignment accuracy by 13.1% and 8.7% respectively. Existing evaluation methods also lack quantitative metrics to adequately measure the pedagogical alignment of LLMs. To address this gap, we propose novel perplexity-based metrics that quantify LLMs' tendency to provide scaffolded guidance versus direct answers, offering a robust measure of pedagogical alignment. Our analysis provides compelling evidence for the superiority of LHP methods over SFT in optimizing LLMs' behavior, underscoring the potential of LHP methods in better aligning LLMs with educational objectives and fostering effective learning experiences. Code and models are available \href{https://github.com/luffycodes/Tutorbot-Spock}{here}., Comment: Accepted at EMNLP 2024 Findings Track

The battery-less Internet of Things (IoT) devices are a key element in the sustainable green initiative for the next-generation wireless networks. These battery-free devices use the ambient energy, harvested from the environment. The energy harvesting environment is dynamic and causes intermittent task execution. The harvested energy is stored in small capacitors and it is challenging to assure the application task execution. The main goal is to provide a mechanism to aggregate the sensor data and provide a sustainable application support in the distributed battery-less IoT network. We model the distributed IoT network system consisting of many battery-free IoT sensor hardware modules and heterogeneous IoT applications that are being supported in the device-edge-cloud continuum. The applications require sensor data from a distributed set of battery-less hardware modules and there is provision of joint control over the module actuators. We propose an application-aware task and energy manager (ATEM) for the IoT devices and a vector-synchronization based data aggregator (VSDA). The ATEM is supported by device-level federated energy harvesting and system-level energy-aware heterogeneous application management. In our proposed framework the data aggregator forecasts the available power from the ambient energy harvester using long-short-term-memory (LSTM) model and sets the device profile as well as the application task rates accordingly. Our proposed scheme meets the heterogeneous application requirements with negligible overhead; reduces the data loss and packet delay; increases the hardware component availability; and makes the components available sooner as compared to the state-of-the-art., Comment: 10 pages, 11 figures

We propose novel evaluations for mathematical reasoning capabilities of Large Language Models (LLMs) based on mathematical misconceptions. Our primary approach is to simulate LLMs as a novice learner and an expert tutor, aiming to identify the incorrect answer to math question resulted from a specific misconception and to recognize the misconception(s) behind an incorrect answer, respectively. Contrary to traditional LLMs-based mathematical evaluations that focus on answering math questions correctly, our approach takes inspirations from principles in educational learning sciences. We explicitly ask LLMs to mimic a novice learner by answering questions in a specific incorrect manner based on incomplete knowledge; and to mimic an expert tutor by identifying misconception(s) corresponding to an incorrect answer to a question. Using simple grade-school math problems, our experiments reveal that, while LLMs can easily answer these questions correctly, they struggle to identify 1) the incorrect answer corresponding to specific incomplete knowledge (misconceptions); 2) the misconceptions that explain particular incorrect answers. Our study indicates new opportunities for enhancing LLMs' math reasoning capabilities, especially on developing robust student simulation and expert tutoring models in the educational applications such as intelligent tutoring systems.

High-quality conversational datasets are crucial for the successful development of Intelligent Tutoring Systems (ITS) that utilize a Large Language Model (LLM) backend. Synthetic student-teacher dialogues, generated using advanced GPT-4 models, are a common strategy for creating these datasets. However, subjects like physics that entail complex calculations pose a challenge. While GPT-4 presents impressive language processing capabilities, its limitations in fundamental mathematical reasoning curtail its efficacy for such subjects. To tackle this limitation, we introduce in this paper an innovative stateful prompt design. Our design orchestrates a mock conversation where both student and tutorbot roles are simulated by GPT-4. Each student response triggers an internal monologue, or `code soliloquy' in the GPT-tutorbot, which assesses whether its subsequent response would necessitate calculations. If a calculation is deemed necessary, it scripts the relevant Python code and uses the Python output to construct a response to the student. Our approach notably enhances the quality of synthetic conversation datasets, especially for subjects that are calculation-intensive. Our preliminary Subject Matter Expert evaluations reveal that our Higgs model, a fine-tuned LLaMA model, effectively uses Python for computations, which significantly enhances the accuracy and computational reliability of Higgs' responses. Code, models, and datasets is available at https://github.com/luffycodes/Tutorbot-Spock-Phys.

We explore whether Large Language Models (LLMs) are capable of logical reasoning with distorted facts, which we call Deduction under Perturbed Evidence (DUPE). DUPE presents a unique challenge to LLMs since they typically rely on their parameters, which encode mostly accurate information, to reason and make inferences. However, in DUPE, LLMs must reason over manipulated or falsified evidence present in their prompts, which can result in false conclusions that are valid only under the manipulated evidence. Our goal with DUPE is to determine whether LLMs can arrive at these false conclusions and identify whether the dominant factor influencing the deduction process is the encoded data in the parameters or the manipulated evidence in the prompts. To evaluate the DUPE capabilities of LLMs, we create a DUPEd version of the StrategyQA dataset, where facts are manipulated to reverse the answer to the question. Our findings show that even the most advanced GPT models struggle to reason on manipulated facts - showcasing poor DUPE skills - with accuracy dropping by 45% compared to the original dataset. We also investigate prompt settings inspired from student simulation models, which mitigate the accuracy drop to some extent. Our findings have practical implications for understanding the performance of LLMs in real-world applications such as student simulation models that involve reasoning over inaccurate information.

This paper investigates the key role of Feed-Forward Networks (FFNs) in transformer models by utilizing the Parallel Attention and Feed-Forward Net Design (PAF) architecture, and comparing it to their Series Attention and Feed-Forward Net Design (SAF) counterparts. Central to the effectiveness of PAF are two main assumptions regarding the FFN block and the attention block within a layer: 1) the primary function of the FFN block is to maintain isotropy among token embeddings and prevent their degeneration, and 2) the residual norm computed in the attention block is substantially smaller than the input token embedding norm. To empirically validate these assumptions, we train PAF variants of two large language models (RoBERTa-large and bert-large-uncased). Our results demonstrate that both assumptions hold true in the PAF design. This study contributes to a deeper understanding of the roles and interactions between FFNs and self-attention mechanisms in transformer architectures.

We present a design framework called Conversational Learning with Analytical Step-by-Step Strategies (CLASS) for building advanced Intelligent Tutoring Systems (ITS) powered by high-performance Large Language Models (LLMs). The CLASS framework empowers ITS with two key capabilities. First, through a carefully curated scaffolding dataset, CLASS equips ITS with essential problem-solving strategies, enabling it to provide tutor-like, step-by-step guidance to students. Second, by using a dynamic conversational dataset, CLASS assists ITS in facilitating natural language interactions, fostering engaging student-tutor conversations. The CLASS framework also provides valuable insights into ITS' internal decision-making process which allows seamless integration of user feedback, thus enabling continuous refinement and improvement. We also present a proof-of-concept ITS, referred to as SPOCK, which is trained using the CLASS framework with a focus on introductory college-level biology content. A carefully constructed protocol was developed for SPOCK's preliminary evaluation, examining aspects such as the factual accuracy and relevance of its responses. Experts in the field of biology offered favorable remarks, particularly highlighting SPOCK's capability to break down questions into manageable subproblems and provide encouraging responses to students. Code and models are available at https://github.com/luffycodes/Tutorbot-Spock., Comment: Paper accepted at EMNLP 2023

This paper investigates the problem of Named Entity Recognition (NER) for extreme low-resource languages with only a few hundred tagged data samples. NER is a fundamental task in Natural Language Processing (NLP). A critical driver accelerating NER systems' progress is the existence of large-scale language corpora that enable NER systems to achieve outstanding performance in languages such as English and French with abundant training data. However, NER for low-resource languages remains relatively unexplored. In this paper, we introduce Mask Augmented Named Entity Recognition (MANER), a new methodology that leverages the distributional hypothesis of pre-trained masked language models (MLMs) for NER. The token in pre-trained MLMs encodes valuable semantic contextual information. MANER re-purposes the token for NER prediction. Specifically, we prepend the token to every word in a sentence for which we would like to predict the named entity tag. During training, we jointly fine-tune the MLM and a new NER prediction head attached to each token. We demonstrate that MANER is well-suited for NER in low-resource languages; our experiments show that for 100 languages with as few as 100 training examples, it improves on state-of-the-art methods by up to 48% and by 12% on average on F1 score. We also perform detailed analyses and ablation studies to understand the scenarios that are best-suited to MANER.

Transformer models trained on massive text corpora have become the de facto models for a wide range of natural language processing tasks. However, learning effective word representations for function words remains challenging. Multimodal learning, which visually grounds transformer models in imagery, can overcome the challenges to some extent; however, there is still much work to be done. In this study, we explore the extent to which visual grounding facilitates the acquisition of function words using stable diffusion models that employ multimodal models for text-to-image generation. Out of seven categories of function words, along with numerous subcategories, we find that stable diffusion models effectively model only a small fraction of function words -- a few pronoun subcategories and relatives. We hope that our findings will stimulate the development of new datasets and approaches that enable multimodal models to learn better representations of function words.

The concept of majorisation is explored as a tool to characterize the performance of a quantum Otto engine in the quasi-static regime. For a working substance in the form of a spin of arbitrary magnitude, majorisation yields a necessary and sufficient condition for the operation of the Otto engine, provided the canonical distribution of the working medium at the hot reservoir is majorised by its canonical distribution at the cold reservoir. For the case of a spin-1/2 interacting with an arbitrary spin via isotropic Heisenberg exchange interaction, we derive sufficient criteria for positive work extraction using the majorisation relation. Finally, local thermodynamics of spins as well as an upper bound on the quantum Otto efficiency is analyzed using the majorisation relation., Comment: RevTex4-2, 24 pages, six figures