English
Related papers

Related papers: Debiasing Reward Models via Causally Motivated Inf…

200 papers

Mitigating social bias in large language models (LLMs) has become an increasingly important research objective. However, existing debiasing methods often incur high human and computational costs, exhibit limited effectiveness, and struggle…

Computation and Language · Computer Science 2025-06-02 Xiaoqing Cheng , Ruizhe Chen , Hongying Zan , Yuxiang Jia , Min Peng

Reinforcement learning based fine-tuning of large language models (LLMs) on human preferences has been shown to enhance both their capabilities and safety behavior. However, in cases related to safety, without precise instructions to human…

Artificial Intelligence · Computer Science 2024-11-05 Tong Mu , Alec Helyar , Johannes Heidecke , Joshua Achiam , Andrea Vallone , Ian Kivlichan , Molly Lin , Alex Beutel , John Schulman , Lilian Weng

Although large language models (LLMs) have demonstrated their effectiveness in a wide range of applications, they have also been observed to perpetuate unwanted biases present in the training data, potentially leading to harm for…

Computation and Language · Computer Science 2026-03-09 Schrasing Tong , Eliott Zemour , Jessica Lu , Rawisara Lohanimit , Lalana Kagal

Large Language Models (LLMs) are increasingly relied upon for solving complex reasoning tasks in domains such as mathematics, logic, and multi-step question answering. A growing line of work seeks to improve reasoning quality by scaling…

Machine Learning · Computer Science 2025-08-05 Seyyed Saeid Cheshmi , Azal Ahmad Khan , Xinran Wang , Zirui Liu , Ali Anwar

Reward models are central to aligning language models with human preferences via reinforcement learning (RL). As RL is increasingly applied to settings such as verifiable rewards and multi-objective alignment, RMs are expected to encode…

Machine Learning · Computer Science 2026-05-21 Jiwoo Hong , Shao Tang , Zhipeng Wang

There has been a lot of interest in understanding what information is captured by hidden representations of language models (LMs). Typically, interpretation methods i) do not guarantee that the model actually uses the encoded information,…

Computation and Language · Computer Science 2021-12-14 Nicola De Cao , Leon Schmid , Dieuwke Hupkes , Ivan Titov

With the introduction of (large) language models, there has been significant concern about the unintended bias such models may inherit from their training data. A number of studies have shown that such models propagate gender stereotypes,…

Computation and Language · Computer Science 2024-08-20 Rameez Qureshi , Naïm Es-Sebbani , Luis Galárraga , Yvette Graham , Miguel Couceiro , Zied Bouraoui

Large Language Models (LLMs) can infer sensitive attributes such as gender or age from indirect cues like names and pronouns, potentially biasing recommendations. While several debiasing methods exist, they require access to the LLMs'…

Information Retrieval · Computer Science 2026-03-16 Mihaela Rotar , Theresia Veronika Rampisela , Maria Maistro

Warning: This paper contains examples of stereotypes and biases. Large Language Models (LLMs) exhibit considerable social biases, and various studies have tried to evaluate and mitigate these biases accurately. Previous studies use…

Computation and Language · Computer Science 2024-07-04 Rem Hida , Masahiro Kaneko , Naoaki Okazaki

Large language models (LLMs), despite their remarkable capabilities, are susceptible to generating biased and discriminatory responses. As LLMs increasingly influence high-stakes decision-making (e.g., hiring and healthcare), mitigating…

Computation and Language · Computer Science 2025-03-04 Jingling Li , Zeyu Tang , Xiaoyu Liu , Peter Spirtes , Kun Zhang , Liu Leqi , Yang Liu

Reward modeling (RM), which captures human preferences to align large language models (LLMs), is increasingly employed in tasks such as model finetuning, response filtering, and ranking. However, due to the inherent complexity of human…

Computation and Language · Computer Science 2026-04-09 Pankayaraj Pathmanathan , Furong Huang

Frontier Large Language Models (LLMs) can be socially discriminatory or sensitive to spurious features of their inputs. Because only well-resourced corporations can train frontier LLMs, we need robust test-time strategies to control such…

Computation and Language · Computer Science 2024-10-08 Leonardo Cotta , Chris J. Maddison

Reinforcement learning from human feedback (RLHF) is widely used to align large language models (LLMs) with human preferences. However, RLHF-trained reward models often exhibit length bias -- a systematic tendency to favor longer responses…

Computation and Language · Computer Science 2025-11-18 Hyeonji Kim , Sujeong Oh , Sanghack Lee

In reinforcement learning from human feedback, preference-based reward models play a central role in aligning large language models to human-aligned behavior. However, recent studies show that these models are prone to reward hacking and…

Artificial Intelligence · Computer Science 2025-10-23 Wenqian Ye , Guangtao Zheng , Aidong Zhang

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…

Computation and Language · Computer Science 2025-06-17 Yan Sun , Stanley Kok

Inference-time scaling techniques have shown promise in enhancing the reasoning capabilities of large language models (LLMs). While recent research has primarily focused on training-time optimization, our work highlights inference-time…

Computation and Language · Computer Science 2026-02-12 Jiachun Li , Pengfei Cao , Zhuoran Jin , Yubo Chen , Jiexin Xu , Huaijun Li , Xiaojian Jiang , Kang Liu , Jun Zhao

Reward models (RMs) play a pivotal role in aligning large language models (LLMs) with human values. However, noisy preferences in human feedback can lead to reward misgeneralization - a phenomenon where reward models learn spurious…

Large language models (LLMs) exhibit social biases that reinforce harmful stereotypes, limiting their safe deployment. Most existing debiasing methods adopt a suppressive paradigm by modifying parameters, prompts, or neurons associated with…

Artificial Intelligence · Computer Science 2026-01-30 Jinhao Pan , Chahat Raj , Anjishnu Mukherjee , Sina Mansouri , Bowen Wei , Shloka Yada , Ziwei Zhu

We explore the internal mechanisms of how bias emerges in large language models (LLMs) when provided with ambiguous comparative prompts: inputs that compare or enforce choosing between two or more entities without providing clear context…

Computation and Language · Computer Science 2024-10-31 Rishabh Adiga , Besmira Nushi , Varun Chandrasekaran

Actively inferring user preferences, for example by asking good questions, is important for any human-facing decision-making system. Active inference allows such systems to adapt and personalize themselves to nuanced individual preferences.…

Computation and Language · Computer Science 2024-06-27 Wasu Top Piriyakulkij , Volodymyr Kuleshov , Kevin Ellis