Related papers: Do Biased Models Have Biased Thoughts?

Despite their strengths, large language models (LLMs) often fail to communicate their confidence accurately, making it difficult to assess when they might be wrong and limiting their reliability. In this work, we demonstrate that reasoning…

Large language models demonstrate strong reasoning capabilities through chain-of-thought prompting, but whether this reasoning quality transfers across languages remains underexplored. We introduce a human-validated framework to evaluate…

This position paper's primary goal is to provoke thoughtful discussion about the relationship between bias and fundamental properties of large language models. I do this by seeking to convince the reader that harmful biases are an…

Ensuring fairness of machine learning systems is a human-in-the-loop process. It relies on developers, users, and the general public to identify fairness problems and make improvements. To facilitate the process we need effective, unbiased,…

Previous work has examined how debiasing language models affect downstream tasks, specifically, how debiasing techniques influence task performance and whether debiased models also make impartial predictions in downstream tasks or not.…

Large Language Models (LLMs) have shown powerful performance and development prospects and are widely deployed in the real world. However, LLMs can capture social biases from unprocessed training data and propagate the biases to downstream…

How biased is a language model? The answer depends on how you ask. A model that refuses to choose between castes for a leadership role will, in a fill-in-the-blank task, reliably associate upper castes with purity and lower castes with lack…

Language models trained to solve reasoning tasks via reinforcement learning have achieved striking results. We refer to these models as reasoning models. Are the Chains of Thought (CoTs) of reasoning models more faithful than traditional…

Reasoning models have attracted increasing attention for their ability to tackle complex tasks, embodying the System II (slow thinking) paradigm in contrast to System I (fast, intuitive responses). Yet a key question remains: Does slower…

Most research on natural language processing treats bias as an absolute concept: Based on a (probably complex) algorithmic analysis, a sentence, an article, or a text is classified as biased or not. Given the fact that for humans the…

Large language models have been extensively studied for emotion recognition and moral reasoning as distinct capabilities, yet the extent to which emotions influence moral judgment remains underexplored. In this work, we develop an…

Large language models have recently demonstrated significant gains in reasoning ability, often attributed to their capacity to generate longer chains of thought and engage in reflective reasoning. However, the contribution of reflections to…

Acquiescence bias, i.e. the tendency of humans to agree with statements in surveys, independent of their actual beliefs, is well researched and documented. Since Large Language Models (LLMs) have been shown to be very influenceable by…

We present the surprising finding that a language model's reasoning capabilities can be improved by training on synthetic datasets of chain-of-thought (CoT) traces from more capable models, even when all of those traces lead to an incorrect…

Pretrained language models are publicly available and constantly finetuned for various real-life applications. As they become capable of grasping complex contextual information, harmful biases are likely increasingly intertwined with those…

Transformer-based pretrained large language models (PLM) such as BERT and GPT have achieved remarkable success in NLP tasks. However, PLMs are prone to encoding stereotypical biases. Although a burgeoning literature has emerged on…

Cognitive biases are systematic deviations in thinking that lead to irrational judgments and problematic decision-making, extensively studied across various fields. Recently, large language models (LLMs) have shown advanced understanding…

This paper investigates the knowledge of language models from the perspective of Bayesian epistemology. We explore how language models adjust their confidence and responses when presented with evidence with varying levels of informativeness…

Recent advances in large language models (LLMs) have led to the development of thinking language models that generate extensive internal reasoning chains before producing responses. While these models achieve improved performance,…

Natural Language Processing (NLP) systems learn harmful societal biases that cause them to amplify inequality as they are deployed in more and more situations. To guide efforts at debiasing these systems, the NLP community relies on a…