English
Related papers

Related papers: Online Iterative Reinforcement Learning from Human…

200 papers

Reinforcement Learning from Human Feedback (RLHF) assumes annotator preferences reflect stable internal states. We challenge this through three experiments spanning the preference pipeline. In a human choice blindness study, 91% of…

Computation and Language · Computer Science 2026-03-10 Wenbin Wu

Despite the promise of RLHF in aligning LLMs with human preferences, it often leads to superficial alignment, prioritizing stylistic changes over improving downstream performance of LLMs. Underspecified preferences could obscure directions…

Computation and Language · Computer Science 2024-03-22 Kyungjae Lee , Dasol Hwang , Sunghyun Park , Youngsoo Jang , Moontae Lee

How can we make models robust to even imperfect human feedback? In reinforcement learning from human feedback (RLHF), human preferences over model outputs are used to train a reward model that assigns scalar values to responses. Because…

Artificial Intelligence · Computer Science 2026-05-11 Tiffany Horter , Andrew Markham , Niki Trigoni , Serena Booth

Reinforcement Learning from Human Feedback (RLHF) has become central to aligning large language models with human values, typically by first learning a reward model from preference data which is then used to update the model with…

Artificial Intelligence · Computer Science 2025-10-20 Keertana Chidambaram , Karthik Vinary Seetharaman , Vasilis Syrgkanis

Aligning large language models (LLM) with human preference plays a key role in building modern generative models and can be achieved by reinforcement learning from human feedback (RLHF). Despite their superior performance, current RLHF…

Machine Learning · Computer Science 2025-02-12 Kaixuan Ji , Jiafan He , Quanquan Gu

Large language models (LLMs) possess strong multilingual capabilities, and combining Reinforcement Learning from Human Feedback (RLHF) with translation tasks has shown great potential. However, we observe that this paradigm performs…

Computation and Language · Computer Science 2025-08-06 Tianjiao Li , Mengran Yu , Chenyu Shi , Yanjun Zhao , Xiaojing Liu , Qiang Zhang , Qi Zhang , Xuanjing Huang , Jiayin Wang

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

Reinforcement Learning from Human Feedback (RLHF) has become central to aligning large language models with human values, typically by first learning a reward model from preference data which is then used to update the model with…

Machine Learning · Computer Science 2025-10-21 Keertana Chidambaram , Karthik Vinay Seetharaman , Vasilis Syrgkanis

Offline algorithms for Reinforcement Learning from Human Preferences (RLHF), which use only a fixed dataset of sampled responses given an input, and preference feedback among these responses, have gained increasing prominence in the…

Machine Learning · Computer Science 2025-02-12 Alekh Agarwal , Christoph Dann , Teodor V. Marinov

Reward functions are difficult to design and often hard to align with human intent. Preference-based Reinforcement Learning (RL) algorithms address these problems by learning reward functions from human feedback. However, the majority of…

Machine Learning · Computer Science 2023-11-28 Joey Hejna , Dorsa Sadigh

Preference-based reinforcement learning (PbRL) provides a powerful paradigm to avoid meticulous reward engineering by learning rewards based on human preferences. However, real-time human feedback is hard to obtain in online tasks. Most…

Machine Learning · Computer Science 2024-12-24 Songjun Tu , Jingbo Sun , Qichao Zhang , Xiangyuan Lan , Dongbin Zhao

Reward modeling represents a long-standing challenge in reinforcement learning from human feedback (RLHF) for aligning language models. Current reward modeling is heavily contingent upon experimental feedback data with high collection…

Computation and Language · Computer Science 2026-03-25 Hao Wang , Haocheng Yang , Licheng Pan , Lei Shen , Xiaoxi Li , Yinuo Wang , Zhichao Chen , Yuan Lu , Haoxuan Li , Zhouchen Lin

Existing approaches to language model alignment often treat safety as a tradeoff against helpfulness, which can lead to unacceptable responses in sensitive domains. To ensure reliable performance in such settings, we propose High-Confidence…

Machine Learning · Computer Science 2025-06-11 Yaswanth Chittepu , Blossom Metevier , Will Schwarzer , Austin Hoag , Scott Niekum , Philip S. Thomas

Designing an effective reward function has long been a challenge in reinforcement learning, particularly for complex tasks in unstructured environments. To address this, various learning paradigms have emerged that leverage different forms…

Machine Learning · Computer Science 2025-04-29 Muhammad Qasim Elahi , Somtochukwu Oguchienti , Maheed H. Ahmed , Mahsa Ghasemi

Reward learning plays a pivotal role in Reinforcement Learning from Human Feedback (RLHF), ensuring the alignment of language models. The Bradley-Terry (BT) model stands as the prevalent choice for capturing human preferences from datasets…

Machine Learning · Computer Science 2024-10-10 Jinsong Liu , Dongdong Ge , Ruihao Zhu

We consider the problem of offline reinforcement learning from human feedback (RLHF) with pairwise comparisons proposed by Zhu et al. (2023), where the implicit reward is a linear function of an unknown parameter. Given an offline dataset,…

Machine Learning · Computer Science 2026-01-23 Zhirui Chen , Vincent Y. F. Tan

Bilevel optimization has been recently applied to many machine learning tasks. However, their applications have been restricted to the supervised learning setting, where static objective functions with benign structures are considered. But…

Machine Learning · Computer Science 2024-06-04 Han Shen , Zhuoran Yang , Tianyi Chen

Aligning large language models (LLMs) with human preferences is crucial for enhancing their utility in terms of helpfulness, truthfulness, safety, harmlessness, and interestingness. Existing methods for achieving this alignment often…

Computation and Language · Computer Science 2024-07-04 Wenhao Liu , Xiaohua Wang , Muling Wu , Tianlong Li , Changze Lv , Zixuan Ling , Jianhao Zhu , Cenyuan Zhang , Xiaoqing Zheng , Xuanjing Huang

This paper presents a novel approach to aligning large language models (LLMs) with individual human preferences, sometimes referred to as Reinforcement Learning from \textit{Personalized} Human Feedback (RLPHF). Given stated preferences…

Artificial Intelligence · Computer Science 2024-07-08 Jin Peng Zhou , Katie Z Luo , Jingwen Gu , Jason Yuan , Kilian Q. Weinberger , Wen Sun

Reinforcement Learning from Human Feedback (RLHF) typically relies on static reward models to align Large Language Models with human preferences. However, human values are inherently diverse and heterogeneous, and a single reward model…

Machine Learning · Computer Science 2026-05-29 Zhenyu Sun , Zheng Xu , Ermin Wei