Related papers: Exploring the Structure of Misconceptions in the F…
We present EDGE, a general-purpose, misconception-aware adaptive learning framework composed of four stages: Evaluate (ability and state estimation), Diagnose (posterior infer-ence of misconceptions), Generate (counterfactual item…
The security of deep learning (DL) systems is an extremely important field of study as they are being deployed in several applications due to their ever-improving performance to solve challenging tasks. Despite overwhelming promises, the…
As post hoc explanation methods are increasingly being leveraged to explain complex models in high-stakes settings, it becomes critical to ensure that the quality of the resulting explanations is consistently high across various population…
Context: Conducting experiments is central to research machine learning research to benchmark, evaluate and compare learning algorithms. Consequently it is important we conduct reliable, trustworthy experiments. Objective: We investigate…
Emergency department triage assigns patients an acuity score that determines treatment priority, and clinical evidence documents persistent gender disparities in human acuity assessment. As hospitals pilot large language models (LLMs) as…
In contrastive learning, two views of an original image, generated by different augmentations, are considered a positive pair, and their similarity is required to be high. Similarly, two views of distinct images form a negative pair, with…
Ensuring fairness in instruments like survey questionnaires or educational tests is crucial. One way to address this is by a Differential Item Functioning (DIF) analysis, which examines if different subgroups respond differently to a…
Contrastive language-image Pre-training (CLIP) [13] can leverage large datasets of unlabeled Image-Text pairs, which have demonstrated impressive performance in various downstream tasks. Given that annotating medical data is time-consuming…
Grades provide students with their primary performance feedback: signals which affect academic choices. Variations in grading practice among courses impose grade penalties (and bonuses) on students who take them. These grade penalties are…
Despite the potential of multi-modal pre-training to learn highly discriminative feature representations from complementary data modalities, current progress is being slowed by the lack of large-scale modality-diverse datasets. By…
Recent studies have demonstrated that deep learning models can discriminate based on protected classes like race and gender. In this work, we evaluate bias present in deepfake datasets and detection models across protected subgroups. Using…
Large Multimodal Models (LMMs) exhibit impressive cross-modal understanding and reasoning abilities, often assessed through multiple-choice questions (MCQs) that include an image, a question, and several options. However, many benchmarks…
In a plethora of recent work, large language models (LLMs) demonstrated impressive reasoning ability, but many proposed downstream reasoning tasks only focus on final answers. Two fundamental questions persist: 1) how consistent is the…
Deep learning models, while achieving remarkable performances, are vulnerable to membership inference attacks (MIAs). Although various defenses have been proposed, there is still substantial room for improvement in the privacy-utility…
Finding general evaluation metrics for unsupervised representation learning techniques is a challenging open research question, which recently has become more and more necessary due to the increasing interest in unsupervised methods. Even…
Counterfactual explanations (CFEs) are an emerging technique under the umbrella of interpretability of machine learning (ML) models. They provide ``what if'' feedback of the form ``if an input datapoint were $x'$ instead of $x$, then an ML…
Concept inventories are standardized assessments that evaluate student understanding of key concepts within academic disciplines. While prevalent across STEM fields, their development lags for advanced computer science topics like dynamic…
To improve Multi-step Mathematical Reasoning (MsMR) of Large Language Models (LLMs), it is crucial to obtain scalable supervision from the corpus by automatically critiquing mistakes in the reasoning process of MsMR and rendering a final…
This paper studies generalized inverse reinforcement learning (GIRL) in Markov decision processes (MDPs), that is, the problem of learning the basic components of an MDP given observed behavior (policy) that might not be optimal. These…
Academic Miscommunication (AM) is the phenomenon of a professor's expectations, beliefs, or goals in the classroom differing from those of the students. In this study, a survey was given to undergraduates in two introductory physics classes…