Algorithmic discrimination is a critical concern as machine learning models are used in high-stakes decision-making in legally protected contexts. Although substantial research on algorithmic bias and discrimination has led to the development of fairness metrics, several critical legal issues remain unaddressed in practice. The paper addresses three key shortcomings in prevailing ML fairness paradigms: (1) the narrow reliance on prediction or outcome disparity as evidence for discrimination, (2) the lack of nuanced evaluation of estimation error and assumptions that the true causal structure and data-generating process are known, and (3) the overwhelming dominance of US-based analyses which has inadvertently fostered some misconceptions regarding lawful modelling practices in other jurisdictions. To address these gaps, we introduce a novel decision-theoretic framework grounded in anti-discrimination law of the United Kingdom, which has global influence and aligns closely with European and Commonwealth legal systems. We propose the "conditional estimation parity" metric, which accounts for estimation error and the underlying data-generating process, aligning with UK legal standards. We apply our formalism to a real-world algorithmic discrimination case, demonstrating how technical and legal reasoning can be aligned to detect and mitigate unlawful discrimination. Our contributions offer actionable, legally-grounded guidance for ML practitioners, policymakers, and legal scholars seeking to develop non-discriminatory automated decision systems that are legally robust.
The article concerns low-rank approximation of matrices generated by sampling a smooth function of two $m$-dimensional variables. We identify several misconceptions surrounding a claim that, for a specific class of analytic functions, such $n \times n$ matrices admit accurate entrywise approximation of rank that is independent of $m$ and grows as $\log(n)$ -- colloquially known as ''big-data matrices are approximately low-rank''. We provide a theoretical explanation of the numerical results presented in support of this claim, describing three narrower classes of functions for which function-generated matrices can be approximated within an entrywise error of order $\varepsilon$ with rank $\mathcal{O}(\log(n) \varepsilon^{-2} \log(\varepsilon^{-1}))$ that is independent of the dimension $m$: (i) functions of the inner product of the two variables, (ii) functions of the Euclidean distance between the variables, and (iii) shift-invariant positive-definite kernels. We extend our argument to tensor-train approximation of tensors generated with functions of the ''higher-order inner product'' of their multiple variables. We discuss our results in the context of low-rank approximation of (a) growing datasets and (b) attention in transformer neural networks.
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}.
High-quality distractors are crucial to both the assessment and pedagogical value of multiple-choice questions (MCQs), where manually crafting ones that anticipate knowledge deficiencies or misconceptions among real students is difficult. Meanwhile, automated distractor generation, even with the help of large language models (LLMs), remains challenging for subjects like math. It is crucial to not only identify plausible distractors but also understand the error behind them. In this paper, we introduce DiVERT (Distractor Generation with Variational Errors Represented as Text), a novel variational approach that learns an interpretable representation of errors behind distractors in math MCQs. Through experiments on a real-world math MCQ dataset with 1,434 questions used by hundreds of thousands of students, we show that DiVERT, despite using a base open-source LLM with 7B parameters, outperforms state-of-the-art approaches using GPT-4o on downstream distractor generation. We also conduct a human evaluation with math educators and find that DiVERT leads to error labels that are of comparable quality to human-authored ones.
Since its introduction in 2022, Generative AI has significantly impacted the art world, from winning state art fairs to creating complex videos from simple prompts. Amid this renaissance, a pivotal issue emerges: should users of Generative AI be recognized as authors eligible for copyright protection? The Copyright Office, in its March 2023 Guidance, argues against this notion. By comparing the prompts to clients' instructions for commissioned art, the Office denies users authorship due to their limited role in the creative process. This Article challenges this viewpoint and advocates for the recognition of Generative AI users who incorporate these tools into their creative endeavors. It argues that the current policy fails to consider the intricate and dynamic interaction between Generative AI users and the models, where users actively influence the output through a process of adjustment, refinement, selection, and arrangement. Rather than dismissing the contributions generated by AI, this Article suggests a simplified and streamlined registration process that acknowledges the role of AI in creation. This approach not only aligns with the constitutional goal of promoting the progress of science and useful arts but also encourages public engagement in the creative process, which contributes to the pool of training data for AI. Moreover, it advocates for a flexible framework that evolves alongside technological advancements while ensuring safety and public interest. In conclusion, by examining text-to-image generators and addressing misconceptions about Generative AI and user interaction, this Article calls for a regulatory framework that adapts to technological developments and safeguards public interests
Intelligent Tutoring Systems (ITS) enhance personalized learning by predicting student answers to provide immediate and customized instruction. However, recent research has primarily focused on the correctness of the answer rather than the student's performance on specific answer choices, limiting insights into students' thought processes and potential misconceptions. To address this gap, we present MCQStudentBert, an answer forecasting model that leverages the capabilities of Large Language Models (LLMs) to integrate contextual understanding of students' answering history along with the text of the questions and answers. By predicting the specific answer choices students are likely to make, practitioners can easily extend the model to new answer choices or remove answer choices for the same multiple-choice question (MCQ) without retraining the model. In particular, we compare MLP, LSTM, BERT, and Mistral 7B architectures to generate embeddings from students' past interactions, which are then incorporated into a finetuned BERT's answer-forecasting mechanism. We apply our pipeline to a dataset of language learning MCQ, gathered from an ITS with over 10,000 students to explore the predictive accuracy of MCQStudentBert, which incorporates student interaction patterns, in comparison to correct answer prediction and traditional mastery-learning feature-based approaches. This work opens the door to more personalized content, modularization, and granular support.
Large vision-language models (VLMs), such as CLIP, have become foundational, demonstrating remarkable success across a variety of downstream tasks. Despite their advantages, these models, akin to other foundational systems, inherit biases from the disproportionate distribution of real-world data, leading to misconceptions about the actual environment. Prevalent datasets like ImageNet are often riddled with non-causal, spurious correlations that can diminish VLM performance in scenarios where these contextual elements are absent. This study presents an investigation into how a simple linear probe can effectively distill task-specific core features from CLIP's embedding for downstream applications. Our analysis reveals that the CLIP text representations are often tainted by spurious correlations, inherited in the biased pre-training dataset. Empirical evidence suggests that relying on visual representations from CLIP, as opposed to text embedding, is more practical to refine the skewed perceptions in VLMs, emphasizing the superior utility of visual representations in overcoming embedded biases. Our codes will be available here.
Multi-agent reinforcement learning (MARL) has exploded in popularity in recent years. While numerous approaches have been developed, they can be broadly categorized into three main types: centralized training and execution (CTE), centralized training for decentralized execution (CTDE), and decentralized training and execution (DTE). CTE methods assume centralization during training and execution (e.g., with fast, free, and perfect communication) and have the most information during execution. CTDE methods are the most common, as they leverage centralized information during training while enabling decentralized execution -- using only information available to that agent during execution. Decentralized training and execution methods make the fewest assumptions and are often simple to implement. This text is an introduction to cooperative MARL -- MARL in which all agents share a single, joint reward. It is meant to explain the setting, basic concepts, and common methods for the CTE, CTDE, and DTE settings. It does not cover all work in cooperative MARL as the area is quite extensive. I have included work that I believe is important for understanding the main concepts in the area and apologize to those that I have omitted. Topics include simple applications of single-agent methods to CTE as well as some more scalable methods that exploit the multi-agent structure, independent Q-learning and policy gradient methods and their extensions, as well as value function factorization methods including the well-known VDN, QMIX, and QPLEX approaches, and centralized critic methods including MADDPG, COMA, and MAPPO. I also discuss common misconceptions, the relationship between different approaches, and some open questions.
Multiple-choice questions (MCQs) are commonly used across all levels of math education since they can be deployed and graded at a large scale. A critical component of MCQs is the distractors, i.e., incorrect answers crafted to reflect student errors or misconceptions. Automatically generating them in math MCQs, e.g., with large language models, has been challenging. In this work, we propose a novel method to enhance the quality of generated distractors through overgenerate-and-rank, training a ranking model to predict how likely distractors are to be selected by real students. Experimental results on a real-world dataset and human evaluation with math teachers show that our ranking model increases alignment with human-authored distractors, although human-authored ones are still preferred over generated ones.
When a teacher provides examples for a student to study, these examples must be informative, enabling a student to progress from their current state toward a target concept or skill. Good teachers must therefore simultaneously infer what students already know and adapt their teaching to students' changing state of knowledge. There is increasing interest in using computational models, particularly large language models, as pedagogical tools. As students, language models in particular have shown a remarkable ability to adapt to new tasks given small numbers of examples. But how effectively can these models adapt as teachers to students of different types? To study this question, we introduce a suite of models and evaluation methods we call AdapT. AdapT has two components: (1) a collection of simulated Bayesian student models that can be used for evaluation of automated teaching methods; (2) a platform for evaluation with human students, to characterize the real-world effectiveness of these methods. We additionally introduce (3) AToM, a new probabilistic model for adaptive teaching that jointly infers students' past beliefs and optimizes for the correctness of future beliefs. In evaluations of simulated students across three learning domains (fraction arithmetic, English morphology, function learning), AToM systematically outperforms LLM-based and standard Bayesian teaching models. In human experiments, both AToM and LLMs outperform non-adaptive random example selection. Our results highlight both the difficulty of the adaptive teaching task and the potential of learned adaptive models for solving it.
Multiple choice questions (MCQs) are a popular method for evaluating students' knowledge due to their efficiency in administration and grading. Crafting high-quality math MCQs is a labor-intensive process that requires educators to formulate precise stems and plausible distractors. Recent advances in large language models (LLMs) have sparked interest in automating MCQ creation, but challenges persist in ensuring mathematical accuracy and addressing student errors. This paper introduces a prototype tool designed to facilitate collaboration between LLMs and educators for streamlining the math MCQ generation process. We conduct a pilot study involving math educators to investigate how the tool can help them simplify the process of crafting high-quality math MCQs. We found that while LLMs can generate well-formulated question stems, their ability to generate distractors that capture common student errors and misconceptions is limited. Nevertheless, a human-AI collaboration has the potential to enhance the efficiency and effectiveness of MCQ generation.
Recently, there has been an increasing interest in the application of multiobjective optimization (MOO) in machine learning (ML). This interest is driven by the numerous real-life situations where multiple objectives must be optimized simultaneously. A key aspect of MOO is the existence of a Pareto set, rather than a single optimal solution, which represents the optimal trade-offs between different objectives. Despite its potential, there is a noticeable lack of satisfactory literature serving as an entry-level guide for ML practitioners aiming to apply MOO effectively. In this paper, our goal is to provide such a resource and highlight pitfalls to avoid. We begin by establishing the groundwork for MOO, focusing on well-known approaches such as the weighted sum (WS) method, alongside more advanced techniques like the multiobjective gradient descent algorithm (MGDA). We critically review existing studies across various ML fields where MOO has been applied and identify challenges that can lead to incorrect interpretations. One of these fields is physics informed neural networks (PINNs), which we use as a guiding example to carefully construct experiments illustrating these pitfalls. By comparing WS and MGDA with one of the most common evolutionary algorithms, NSGA-II, we demonstrate that difficulties can arise regardless of the specific MOO method used. We emphasize the importance of understanding the specific problem, the objective space, and the selected MOO method, while also noting that neglecting factors such as convergence criteria can result in misleading experiments.
The prevalence of unwarranted beliefs, spanning pseudoscience, logical fallacies, and conspiracy theories, presents substantial societal hurdles and the risk of disseminating misinformation. Utilizing established psychometric assessments, this study explores the capabilities of large language models (LLMs) vis-a-vis the average human in detecting prevalent logical pitfalls. We undertake a philosophical inquiry, juxtaposing the rationality of humans against that of LLMs. Furthermore, we propose methodologies for harnessing LLMs to counter misconceptions, drawing upon psychological models of persuasion such as cognitive dissonance theory and elaboration likelihood theory. Through this endeavor, we highlight the potential of LLMs as personalized misinformation debunking agents.
Classification systems are evaluated in a countless number of papers. However, we find that evaluation practice is often nebulous. Frequently, metrics are selected without arguments, and blurry terminology invites misconceptions. For instance, many works use so-called 'macro' metrics to rank systems (e.g., 'macro F1') but do not clearly specify what they would expect from such a `macro' metric. This is problematic, since picking a metric can affect research findings, and thus any clarity in the process should be maximized. Starting from the intuitive concepts of bias and prevalence, we perform an analysis of common evaluation metrics. The analysis helps us understand the metrics' underlying properties, and how they align with expectations as found expressed in papers. Then we reflect on the practical situation in the field, and survey evaluation practice in recent shared tasks. We find that metric selection is often not supported with convincing arguments, an issue that can make a system ranking seem arbitrary. Our work aims at providing overview and guidance for more informed and transparent metric selection, fostering meaningful evaluation.
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.
Understanding input substitution and output transformation possibilities is critical for efficient resource allocation and firm strategy. There are important examples of fixed proportion technologies where certain inputs are non-substitutable and/or certain outputs are non-transformable. However, there is widespread confusion about the appropriate modeling of fixed proportion technologies in data envelopment analysis. We point out and rectify several misconceptions in the existing literature, and show how fixed proportion technologies can be correctly incorporated into the axiomatic framework. A Monte Carlo study is performed to demonstrate the proposed solution.
Data-driven approaches have revolutionized scientific research, with machine learning and statistical analysis being commonly used methodologies. Despite their widespread use, these approaches differ significantly in their techniques, objectives and implementations. Few studies have systematically applied both methods to identical datasets to highlight potential differences, particularly in language and cognitive sciences. This study employs the Buckeye Speech Corpus to illustrate how machine learning and statistical analysis are applied in data-driven research to obtain distinct insights on language production. We demonstrate the theoretical differences, implementation steps, and unique objectives of each approach through a comprehensive, tutorial-like comparison. Our analysis reveals that while machine learning excels at pattern recognition and prediction, statistical methods provide deeper insights into relationships between variables. The study highlights how semantic relevance, a novel metric measuring contextual influence on target words, contributes to understanding word duration in speech. We also systematically compare the differences between regression models used in machine learning and statistical analysis, particularly focusing on the training and fitting processes. Additionally, we clarify several common misconceptions that contribute to the confusion between these two approaches. Overall, by elucidating the complementary strengths of machine learning and statistics, this research enhances our understanding of diverse data-driven strategies in language and cognitive sciences, offering researchers valuable guidance on when and how to effectively apply these approaches in different research contexts.
Historically, females were excluded from clinical research due to their reproductive roles, hindering medical understanding and healthcare quality. Despite guidelines promoting equal participation, females are underrepresented in exercise science, perpetuating misconceptions about female physiology. Even less attention has been given to exercise in the pregnant population. Research on pregnancy and exercise has evolved considerably from the initial bedrest prescriptions but concerns about exercise risks during pregnancy persisted for many decades. Recent guidelines endorse moderate-intensity physical activity during pregnancy, supported by considerable evidence of its safety and benefits. Mental health during pregnancy, often overlooked, is gaining traction, with exercise showing promise in reducing depression and anxiety. While pregnancy guidelines recommend moderate-intensity physical activity, there remains limited understanding of optimal frequency, intensity, type and time (duration) for extremes like elite athletes or those with complications. Female participation in elite sport and physically demanding jobs is rising, but research on their specific needs is lacking. Traditional practices like bed rest for high-risk pregnancies are being questioned, as evidence suggests it may not improve outcomes. Historical neglect of gestational parents in research perpetuated stereotypes of female frailty, but recent years have seen a shift towards recognizing the benefits of an active pregnancy. Closing knowledge gaps and inclusivity in research are crucial for ensuring guidelines reflect the diverse needs of gestational parents. Therefore, the purpose of this review is to summarize the evolution of exercise physiology and pregnancy research along with future directions for this novel field.
Federated learning (FL) facilitates collaborative model training among multiple clients without raw data exposure. However, recent studies have shown that clients' private training data can be reconstructed from shared gradients in FL, a vulnerability known as gradient inversion attacks (GIAs). While GIAs have demonstrated effectiveness under \emph{ideal settings and auxiliary assumptions}, their actual efficacy against \emph{practical FL systems} remains under-explored. To address this gap, we conduct a comprehensive study on GIAs in this work. We start with a survey of GIAs that establishes a timeline to trace their evolution and develops a systematization to uncover their inherent threats. By rethinking GIA in practical FL systems, three fundamental aspects influencing GIA's effectiveness are identified: \textit{training setup}, \textit{model}, and \textit{post-processing}. Guided by these aspects, we perform extensive theoretical and empirical evaluations of SOTA GIAs across diverse settings. Our findings highlight that GIA is notably \textit{constrained}, \textit{fragile}, and \textit{easily defensible}. Specifically, GIAs exhibit inherent limitations against practical local training settings. Additionally, their effectiveness is highly sensitive to the trained model, and even simple post-processing techniques applied to gradients can serve as effective defenses. Our work provides crucial insights into the limited threats of GIAs in practical FL systems. By rectifying prior misconceptions, we hope to inspire more accurate and realistic investigations on this topic.
Multiple-choice questions (MCQs) are ubiquitous in almost all levels of education since they are easy to administer, grade, and are a reliable format in assessments and practices. One of the most important aspects of MCQs is the distractors, i.e., incorrect options that are designed to target common errors or misconceptions among real students. To date, the task of crafting high-quality distractors largely remains a labor and time-intensive process for teachers and learning content designers, which has limited scalability. In this work, we study the task of automated distractor generation in the domain of math MCQs and explore a wide variety of large language model (LLM)-based approaches, from in-context learning to fine-tuning. We conduct extensive experiments using a real-world math MCQ dataset and find that although LLMs can generate some mathematically valid distractors, they are less adept at anticipating common errors or misconceptions among real students.