Related papers: Do Biased Models Have Biased Thoughts?

Pre-trained language models (PLMs) are trained on data that inherently contains gender biases, leading to undesirable impacts. Traditional debiasing methods often rely on external corpora, which may lack quality, diversity, or demographic…

Extended-thinking models expose a second text-generation channel ("thinking tokens") alongside the user-visible answer. This study examines 12 open-weight reasoning models on MMLU and GPQA questions paired with misleading hints. Among the…

Large Language Models (LLMs) have emerged as powerful candidates to inform clinical decision-making processes. While these models play an increasingly prominent role in shaping the digital landscape, two growing concerns emerge in…

A dangerous assumption that can be made from prior work on the bias transfer hypothesis (BTH) is that biases do not transfer from pre-trained large language models (LLMs) to adapted models. We invalidate this assumption by studying the BTH…

Research on mental state reasoning in language models (LMs) has the potential to inform theories of human social cognition--such as the theory that mental state reasoning emerges in part from language exposure--and our understanding of LMs…

Chain-of-Thought (CoT) reasoning has significantly advanced state-of-the-art AI capabilities. However, recent studies have shown that CoT reasoning is not always faithful when models face an explicit bias in their prompts, i.e., the CoT can…

Chain-of-thought (CoT) reasoning has been proposed as a transparency mechanism for large language models in safety-critical deployments, yet its effectiveness depends on faithfulness (whether models accurately verbalize the factors that…

The creation of benchmarks to evaluate the safety of Large Language Models is one of the key activities within the trusted AI community. These benchmarks allow models to be compared for different aspects of safety such as toxicity, bias,…

Researchers have devised numerous ways to quantify social biases vested in pretrained language models. As some language models are capable of generating coherent completions given a set of textual prompts, several prompting datasets have…

Large language models (LLMs) often exhibit strong biases, e.g, against women or in favor of the number 7. We investigate whether LLMs would be able to output less biased answers when allowed to observe their prior answers to the same…

_Uncertainty expressions_ such as "probably" or "highly unlikely" are pervasive in human language. While prior work has established that there is population-level agreement in terms of how humans quantitatively interpret these expressions,…

Large Language Models (LLMs) are trained on large corpora written by humans and demonstrate high performance on various tasks. However, as humans are susceptible to cognitive biases, which can result in irrational judgments, LLMs can also…

Traditional discussions of bias in large language models focus on a conception of bias closely tied to unfairness, especially as affecting marginalized groups. Recent work raises the novel possibility of assessing the outputs of large…

We study fairness in Machine Learning (FairML) through the lens of attribute-based explanations generated for machine learning models. Our hypothesis is: Biased Models have Biased Explanations. To establish that, we first translate existing…

This paper delves into the capabilities of large language models (LLMs), specifically focusing on advancing the theoretical comprehension of chain-of-thought prompting. We investigate how LLMs can be effectively induced to generate a…

Recent advances in large language models (LLMs) have enabled automatic generation of chain-of-thought (CoT) reasoning, leading to strong performance on tasks such as math and code. However, when reasoning steps reflect social stereotypes…

Large Language Models (LLMs) have become foundational in modern language-driven software applications, profoundly influencing daily life. A critical technique in leveraging their potential is role-playing, where LLMs simulate diverse roles…

Previous works on the fairness of toxic language classifiers compare the output of models with different identity terms as input features but do not consider the impact of other important concepts present in the context. Here, besides…

Standard benchmarks of bias and fairness in large language models (LLMs) measure the association between the user attributes stated or implied by a prompt and the LLM's short text response, but human-AI interaction increasingly requires…

This work presents a comprehensive evaluation of how quantization affects model bias, with particular attention to its impact on individual demographic subgroups. We focus on weight and activation quantization strategies and examine their…