Related papers: Do Biased Models Have Biased Thoughts?

The relationship between language and thought remains an unresolved philosophical issue. Existing viewpoints can be broadly categorized into two schools: one asserting their independence, and another arguing that language constrains…

The rapid advancement of large language models (LLMs) and their growing integration into daily life underscore the importance of evaluating and ensuring their fairness. In this work, we examine fairness within the domain of emotional theory…

Do large language models (LLMs) display rational reasoning? LLMs have been shown to contain human biases due to the data they have been trained on; whether this is reflected in rational reasoning remains less clear. In this paper, we answer…

While reasoning-based large language models excel at complex tasks through an internal, structured thinking process, a concerning phenomenon has emerged that such a thinking process can aggregate social stereotypes, leading to biased…

Spurious correlations were found to be an important factor explaining model performance in various NLP tasks (e.g., gender or racial artifacts), often considered to be ''shortcuts'' to the actual task. However, humans tend to similarly make…

Large Language Models (LLMs) can achieve strong performance on many tasks by producing step-by-step reasoning before giving a final output, often referred to as chain-of-thought reasoning (CoT). It is tempting to interpret these CoT…

Large language models (LLMs) exhibit cognitive biases -- systematic tendencies of irrational decision-making, similar to those seen in humans. Prior work has found that these biases vary across models and can be amplified by instruction…

Large language models (LLMs) are increasingly deployed in socially sensitive settings despite substantial documentation that they encode gender biases. Chain-of-Thought (CoT) prompting has been proposed as a bias-mitigation approach.…

Despite the success of chain of thought in enhancing language model reasoning, the underlying process remains less well understood. Although logically sound reasoning appears inherently crucial for chain of thought, prior studies…

The societal impact of pre-trained language models has prompted researchers to probe them for strong associations between protected attributes and value-loaded terms, from slur to prestigious job titles. Such work is said to probe models…

This paper investigates the influence of cognitive biases on Large Language Models (LLMs) outputs. Cognitive biases, such as confirmation and availability biases, can distort user inputs through prompts, potentially leading to unfaithful…

Confirmation bias is a cognitive bias that adversely affects management decisions, and mathematical modelling is an aid to its detailed understanding. Bias in opinion update about the value of a parameter is modelled here assuming that…

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,…

Chain-of-thought prompting (CoT) has the potential to improve the explainability of language model reasoning. But CoT can also systematically misrepresent the factors influencing models' behavior -- for example, rationalizing answers in…

We explore how generating a chain of thought -- a series of intermediate reasoning steps -- significantly improves the ability of large language models to perform complex reasoning. In particular, we show how such reasoning abilities emerge…

Gender, race and social biases have recently been detected as evident examples of unfairness in applications of Natural Language Processing. A key path towards fairness is to understand, analyse and interpret our data and algorithms. Recent…

Humans have a powerful and mysterious capacity to reason. Working through a set of mental steps enables us to make inferences we would not be capable of making directly even though we get no additional data from the world. Similarly, when…

System 2 reasoning is one of the defining characteristics of intelligence, which requires slow and logical thinking. Human conducts System 2 reasoning via the language of thoughts that organizes the reasoning process as a causal sequence of…

Human biases have been shown to influence the performance of models and algorithms in various fields, including Natural Language Processing. While the study of this phenomenon is garnering focus in recent years, the available resources are…

The widespread adoption of large language models (LLMs) underscores the urgent need to ensure their fairness. However, LLMs frequently present dominant viewpoints while ignoring alternative perspectives from minority parties, resulting in…