Related papers: Exploring the Structure of Misconceptions in the F…
As Large Language Models (LLMs) are nondeterministic, the same input can generate different outputs, some of which may be incorrect or hallucinated. If run again, the LLM may correct itself and produce the correct answer. Unfortunately,…
Reasoning models are evaluated on single-turn benchmarks but deployed in multi-turn dialogue, where users push back on correct answers. Under sustained adversarial pressure we find a previously undocumented failure mode: the…
Constraint inference is widely considered essential to align reinforcement learning agents with safety boundaries and operational guidelines by observing expert demonstrations. However, existing approaches typically assume homogeneous…
Multimodal large language models (MLLMs) have recently achieved state-of-the-art performance on tasks ranging from visual question answering to video understanding. However, existing studies have concentrated mainly on visual-textual…
The increased use of multiple-choice (MC) questions in introductory-level physics final exams is largely hindered by reservations about its ability to test the broad cognitive domain that is routinely accessed with typical…
Non-linear dynamics is probably much more common in the epigenetic dynamics of living beings than hitherto recognized. Here we report a case of global bifurcation triggered by gender that affects higher cognitive functions in humans. We…
Automatic Gender Recognition (AGR) systems are an increasingly widespread application in the Machine Learning (ML) landscape. While these systems are typically understood as detecting gender, they often classify datapoints based on…
Model Inversion (MI), in which an adversary abuses access to a trained Machine Learning (ML) model attempting to infer sensitive information about its original training data, has attracted increasing research attention. During MI, the…
The research of machine learning (ML) algorithms for human activity recognition (HAR) has made significant progress with publicly available datasets. However, most research prioritizes statistical metrics over examining negative sample…
Contrastive learning have been widely used as pretext tasks for self-supervised pre-trained molecular representation learning models in AI-aided drug design and discovery. However, exiting methods that generate molecular views by…
The objective of the Multiple Appropriate Facial Reaction Generation (MAFRG) task is to produce contextually appropriate and diverse listener facial behavioural responses based on the multimodal behavioural data of the conversational…
Multimodal Emotion Recognition (MER) has attracted growing attention with the rapid advancement of human-computer interaction. However, different modalities exhibit substantial discrepancies in semantics, quality, and availability, leading…
The existence of gender differences in student performance on conceptual assessments and their responses to attitudinal assessments has been repeatedly demonstrated. This difference is often present in students' preinstruction responses and…
The recent prevalence of publicly accessible, large medical imaging datasets has led to a proliferation of artificial intelligence (AI) models for cardiovascular image classification and analysis. At the same time, the potentially…
Data from multifactor HCI experiments often violates the normality assumption of parametric tests (i.e., nonconforming data). The Aligned Rank Transform (ART) is a popular nonparametric analysis technique that can find main and interaction…
Multiple Instance Learning (MIL) is a sub-domain of classification problems with positive and negative labels and a "bag" of inputs, where the label is positive if and only if a positive element is contained within the bag, and otherwise is…
The performance of a binary classifier is described by a confusion matrix with four entries: the number of true positives (TP), true negatives (TN), false positives (FP), and false negatives (FN). The Matthews Correlation Coefficient (MCC),…
The 2017 Fake News Challenge Stage 1 (FNC-1) shared task addressed a stance classification task as a crucial first step towards detecting fake news. To date, there is no in-depth analysis paper to critically discuss FNC-1's experimental…
Student experiences and empirical studies report that "black box" AI text detectors produce high false positive rates with disproportionate errors against certain student populations, yet typically theoretical analyses model detection as a…
Group work during lab instruction can be a source of inequity between male and female students. In this preliminary study, we explored the activities male and female students take on during a lab session at a university in Denmark.…