Related papers: Auditing Stance Asymmetry in Generative Explanatio…

With machine learning models being increasingly applied to various decision-making scenarios, people have spent growing efforts to make machine learning models more transparent and explainable. Among various explanation techniques,…

In contested domains, instruction-tuned language models must balance user-alignment pressures against faithfulness to the in-context evidence. To evaluate this tension, we introduce a controlled epistemic-conflict framework grounded in the…

Counterfactual explanations (CEs) aim to enhance the interpretability of machine learning models by illustrating how alterations in input features would affect the resulting predictions. Common CE approaches require an additional model and…

Systems analysis students increasingly use Generative AI, yet current pedagogy lacks systematic approaches for teaching responsible AI orchestration that fosters critical thinking whilst meeting educational outcomes. Students risk accepting…

A key assumption of most statistical machine learning methods is that they have access to independent samples from the distribution of data they encounter at test time. As such, these methods often perform poorly in the face of biased data,…

This work proposes Adaptive Facilitated Mutation, a self-adaptive mutation method for Structured Grammatical Evolution (SGE), biologically inspired by the theory of facilitated variation. In SGE, the genotype of individuals contains a list…

Speech Integrated Large Language Models (SILLMs) combine large language models with speech perception to perform diverse tasks, such as emotion recognition to speaker verification, demonstrating universal audio understanding capability.…

Social bias in language - towards genders, ethnicities, ages, and other social groups - poses a problem with ethical impact for many NLP applications. Recent research has shown that machine learning models trained on respective data may not…

Every formal grammar defines a language and can in principle be used in three ways: to generate strings (production), to recognize them (parsing), or -- given only examples -- to infer the grammar itself (grammar induction). Generation and…

Bias in Large Language Models (LLMs) significantly undermines their reliability and fairness. We focus on a common form of bias: when two reference concepts in the model's concept space, such as sentiment polarities (e.g., "positive" and…

Language models have become very popular recently and many claims have been made about their abilities, including for commonsense reasoning. Given the increasingly better results of current language models on previous static benchmarks for…

Large-scale multimodal contrastive learning has recently achieved impressive success in learning rich and transferable representations, yet it remains fundamentally limited by the uniform treatment of feature dimensions and the neglect of…

Learning to compare two objects are essential in applications, such as digital forensics, face recognition, and brain network analysis, especially when labeled data is scarce and imbalanced. As these applications make high-stake decisions…

Sparse autoencoders (SAEs) have emerged as a promising approach in language model interpretability, offering unsupervised extraction of sparse features. For interpretability methods to succeed, they must identify abstract features across…

While large language models (LLMs) play increasingly significant roles in society, research shows they continue to generate content that reflects social bias against sensitive groups. Existing benchmarks effectively identify these biases,…

Analyzing large-scale text corpora is a core challenge in machine learning, crucial for tasks like identifying undesirable model behaviors or biases in training data. Current methods often rely on costly LLM-based techniques (e.g.…

The rapid advancement of Vision-Language models (VLMs) has raised growing concerns that their black-box reasoning processes could lead to unintended forms of social bias. Current debiasing approaches focus on mitigating surface-level bias…

Word sense disambiguation (WSD), which aims to determine an appropriate sense for a target word given its context, is crucial for natural language understanding. Existing supervised methods treat WSD as a classification task and have…

Instruction-tuned language models exhibit behavioural fairness in high-stakes decisions while retaining biased associations in their internal representations. However, whether these suppressed representations can affect model outputs - and…

Sparse autoencoders (SAEs) have lately been used to uncover interpretable latent features in large language models. By projecting dense embeddings into a much higher-dimensional and sparse space, learned features become disentangled and…