Related papers: Auditing Stance Asymmetry in Generative Explanatio…

Interpretability is a pressing issue for decision systems. Many post hoc methods have been proposed to explain the predictions of a single machine learning model. However, business processes and decision systems are rarely centered around a…

Large language models (LLMs) have demonstrated remarkable capabilities in simulating human behaviour and social intelligence. However, they risk perpetuating societal biases, especially when demographic information is involved. We introduce…

Large language models produce repetitive output when prompted independently across many batches, a phenomenon we term cross-batch mode collapse: the progressive loss of output diversity when a language model is prompted repeatedly without…

Many modern AI question-answering systems convert text into vectors and retrieve the closest matches to a user question. While effective for topical similarity, similarity scores alone do not explain why some retrieved text can serve as…

Speech emotion recognition (SER) systems often exhibit gender bias. However, the effectiveness and robustness of existing debiasing methods in such multi-label scenarios remain underexplored. To address this gap, we present EMO-Debias, a…

Variational autoencoders (VAEs) and other generative methods have garnered growing interest not just for their generative properties but also for the ability to dis-entangle a low-dimensional latent variable space. However, few existing…

Sarcasm detection is a crucial yet challenging Natural Language Processing task. Existing Large Language Model methods are often limited by single-perspective analysis, static reasoning pathways, and a susceptibility to hallucination when…

The development of unbiased large language models is widely recognized as crucial, yet existing benchmarks fall short in detecting biases due to limited scope, contamination, and lack of a fairness baseline. SAGED(bias) is the first…

Machine learning (ML) algorithms are increasingly deployed in high-stakes decision-making domains such as loan approvals, hiring, and recidivism predictions. While existing fairness metrics (e.g., statistical parity, equal opportunity)…

To examine whether intersectional bias can be observed in language generation, we examine \emph{GPT-2} and \emph{GPT-NEO} models, ranging in size from 124 million to ~2.7 billion parameters. We conduct an experiment combining up to three…

Sparse autoencoders (SAEs) have shown promise in extracting interpretable features from complex neural networks. We present one of the first applications of SAEs to dense text embeddings from large language models, demonstrating their…

Explainable artificial intelligence (XAI) is concerned with producing explanations indicating the inner workings of models. For a Rashomon set of similarly performing models, explanations provide a way of disambiguating the behavior of…

Fine-grained sentiment analysis faces ongoing challenges in Aspect Sentiment Triple Extraction (ASTE), particularly in accurately capturing the relationships between aspects, opinions, and sentiment polarities. While researchers have made…

As language models (LMs) become increasingly powerful and widely used, it is important to quantify them for sociodemographic bias with potential for harm. Prior measures of bias are sensitive to perturbations in the templates designed to…

This paper thoroughly investigates a range of popular DE configurations to identify components responsible for the emergence of structural bias - recently identified tendency of the algorithm to prefer some regions of the search space for…

Generative artificial intelligence is increasingly being integrated into complex business workflows, fundamentally shifting the boundaries of managerial decision-making. However, the reliability of its strategic advice in ambiguous business…

In this paper, we focus on the problem of unsupervised image-sentence matching. Existing research explores to utilize document-level structural information to sample positive and negative instances for model training. Although the approach…

Existing studies on bias mitigation methods for large language models (LLMs) use diverse baselines and metrics to evaluate debiasing performance, leading to inconsistent comparisons among them. Moreover, their evaluations are mostly based…

Unsupervised sentence embedding aims to obtain the most appropriate embedding for a sentence to reflect its semantic. Contrastive learning has been attracting developing attention. For a sentence, current models utilize diverse data…

Sociodemographic bias in language models (LMs) has the potential for harm when deployed in real-world settings. This paper presents a comprehensive survey of the past decade of research on sociodemographic bias in LMs, organized into a…