English
Related papers

Related papers: Reward Shaping to Mitigate Reward Hacking in RLHF

200 papers

Reinforcement Learning from Human Feedback (RLHF) aligns language models with human preferences but is computationally expensive. We explore two approaches that leverage human gaze modeling to enhance RLHF: (1) gaze-aware reward models and…

Machine Learning · Computer Science 2025-07-17 Karim Galliamov , Ivan Titov , Ilya Pershin

Reinforcement Learning from Human Feedback (RLHF) and related alignment paradigms have become central to steering large language models (LLMs) and multimodal large language models (MLLMs) toward human-preferred behaviors. However, these…

Personalizing large language models (LLMs) to accommodate diverse user preferences is essential for enhancing alignment and user satisfaction. Traditional reinforcement learning from human feedback (RLHF) approaches often rely on monolithic…

Machine Learning · Computer Science 2025-04-22 Avinandan Bose , Zhihan Xiong , Yuejie Chi , Simon Shaolei Du , Lin Xiao , Maryam Fazel

To design rewards that align with human goals, Reinforcement Learning from Human Feedback (RLHF) has emerged as a prominent technique for learning reward functions from human preferences and optimizing policies via reinforcement learning…

Machine Learning · Computer Science 2025-05-14 Taehyun Cho , Seokhun Ju , Seungyub Han , Dohyeong Kim , Kyungjae Lee , Jungwoo Lee

Reinforcement learning from human feedback (RLHF) is an essential technique for ensuring that large language models (LLMs) are aligned with human values and preferences during the post-training phase. As an effective RLHF approach, group…

Machine Learning · Computer Science 2025-06-18 Zonglin Yang , Zhexuan Gu , Houduo Qi , Yancheng Yuan

Designing a reinforcement learning from human feedback (RLHF) algorithm to approximate a human's unobservable reward function requires assuming, implicitly or explicitly, a model of human preferences. A preference model that poorly…

Machine Learning · Computer Science 2026-04-14 Stephane Hatgis-Kessell , W. Bradley Knox , Serena Booth , Peter Stone

Reinforcement Learning from Human Feedback (RLHF) has emerged as a popular paradigm for aligning models with human intent. Typically RLHF algorithms operate in two phases: first, use human preferences to learn a reward function and second,…

Machine Learning · Computer Science 2024-05-01 Joey Hejna , Rafael Rafailov , Harshit Sikchi , Chelsea Finn , Scott Niekum , W. Bradley Knox , Dorsa Sadigh

Reinforcement Learning from Human Feedback (RLHF) plays a crucial role in aligning large language models (LLMs) with human values and preferences. However, the quality and stability of the trained reward model largely determine the final…

Machine Learning · Computer Science 2025-12-17 Chunjin Jian , Xinhua Zhu

Reinforcement learning from human feedback (RLHF) provides a principled framework for aligning AI systems with human preference data. For various reasons, e.g., personal bias, context ambiguity, lack of training, etc, human annotators may…

Machine Learning · Computer Science 2024-07-10 Alexander Bukharin , Ilgee Hong , Haoming Jiang , Zichong Li , Qingru Zhang , Zixuan Zhang , Tuo Zhao

Human-designed reward functions for reinforcement learning (RL) agents are frequently misaligned with the humans' true, unobservable objectives, and thus act only as proxies. Optimizing for a misspecified proxy reward function often induces…

Artificial Intelligence · Computer Science 2026-01-30 Stephane Hatgis-Kessell , Logan Mondal Bhamidipaty , Emma Brunskill

Current audio captioning relies on supervised learning with paired audio-caption data, which is costly to curate and may not reflect human preferences in real-world scenarios. To address this, we propose a preference-aligned audio…

Audio and Speech Processing · Electrical Eng. & Systems 2026-02-26 Kartik Hegde , Rehana Mahfuz , Yinyi Guo , Erik Visser

Aligning human preference and value is an important requirement for contemporary foundation models. State-of-the-art techniques such as Reinforcement Learning from Human Feedback (RLHF) often consist of two stages: 1) supervised fine-tuning…

Artificial Intelligence · Computer Science 2024-10-29 Jiaxiang Li , Siliang Zeng , Hoi-To Wai , Chenliang Li , Alfredo Garcia , Mingyi Hong

Reinforcement Learning from Human Feedback (RLHF) has emerged as a pivotal technique for aligning artificial intelligence systems with human values, achieving remarkable success in fine-tuning large language models. However, existing RLHF…

Machine Learning · Computer Science 2025-03-26 Renpu Liu , Peng Wang , Donghao Li , Cong Shen , Jing Yang

Reinforcement learning with human feedback (RLHF) is an emerging paradigm to align models with human preferences. Typically, RLHF aggregates preferences from multiple individuals who have diverse viewpoints that may conflict with each…

Machine Learning · Computer Science 2024-03-11 Huiying Zhong , Zhun Deng , Weijie J. Su , Zhiwei Steven Wu , Linjun Zhang

Reward models (RMs) are central to reinforcement learning from human feedback (RLHF), providing the critical supervision signals that align large language models (LLMs) with human preferences. Generative reward models (GRMs) provide greater…

Machine Learning · Computer Science 2026-04-21 Ai Jian , Jingqing Ruan , Xing Ma , Xiaoyun Zhang , Dailin Li , Weipeng Zhang , Ke Zeng , Xunliang Cai

Current RLHF methods such as PPO and DPO typically reduce human preferences to binary labels, which are costly to obtain and too coarse to reflect individual variation. We observe that expressions of satisfaction and dissatisfaction follow…

Computation and Language · Computer Science 2025-10-28 YuXuan Zhang

Reinforcement Learning from Human Feedback (RLHF) remains vulnerable to reward hacking, where models exploit spurious correlations in learned reward models to achieve high scores while violating human intent. Existing mitigations rely on…

Artificial Intelligence · Computer Science 2026-02-03 Mohammad Beigi , Ming Jin , Junshan Zhang , Qifan Wang , Lifu Huang

Reinforcement learning from human feedback (RLHF) has emerged as the primary method for aligning large language models (LLMs) with human preferences. The RLHF process typically starts by training a reward model (RM) using human preference…

Machine Learning · Computer Science 2024-06-19 Haoxiang Wang , Wei Xiong , Tengyang Xie , Han Zhao , Tong Zhang

Reward shaping is a technique in reinforcement learning that addresses the sparse-reward problem by providing more frequent and informative rewards. We introduce a self-adaptive and highly efficient reward shaping mechanism that…

Machine Learning · Computer Science 2025-03-03 Haozhe Ma , Zhengding Luo , Thanh Vinh Vo , Kuankuan Sima , Tze-Yun Leong

Reinforcement Learning from Human Feedback (\textbf{RLHF}) has emerged as a dominant approach for aligning LLM outputs with human preferences. Inspired by the success of RLHF, we study the performance of multiple algorithms that learn from…