English
Related papers

Related papers: Cost-Effective Proxy Reward Model Construction wit…

200 papers

The goal of aligning language models to human preferences requires data that reveal these preferences. Ideally, time and money can be spent carefully collecting and tailoring bespoke preference data to each downstream application. However,…

Artificial Intelligence · Computer Science 2024-09-17 Judy Hanwen Shen , Archit Sharma , Jun Qin

Preference optimization, particularly through Reinforcement Learning from Human Feedback (RLHF), has achieved significant success in aligning Large Language Models (LLMs) to adhere to human intentions. Unlike offline alignment with a fixed…

Machine Learning · Computer Science 2024-11-06 Shenao Zhang , Donghan Yu , Hiteshi Sharma , Han Zhong , Zhihan Liu , Ziyi Yang , Shuohang Wang , Hany Hassan , Zhaoran Wang

In this paper, we investigate the problem of offline Preference-based Reinforcement Learning (PbRL) with human feedback where feedback is available in the form of preference between trajectory pairs rather than explicit rewards. Our…

Machine Learning · Computer Science 2023-10-03 Wenhao Zhan , Masatoshi Uehara , Nathan Kallus , Jason D. Lee , Wen Sun

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…

Iterative data generation and model retraining are widely used to align large language models (LLMs). It typically involves a policy model to generate on-policy responses and a reward model to guide training data selection. Direct…

Computation and Language · Computer Science 2025-07-01 Yao Xiao , Hai Ye , Linyao Chen , Hwee Tou Ng , Lidong Bing , Xiaoli Li , Roy Ka-wei Lee

Aligning large language models (LLMs) with human values is an increasingly critical step in post-training. Direct Preference Optimization (DPO) has emerged as a simple, yet effective alternative to reinforcement learning from human feedback…

Artificial Intelligence · Computer Science 2025-07-29 Yifan Wang , Runjin Chen , Bolian Li , David Cho , Yihe Deng , Ruqi Zhang , Tianlong Chen , Zhangyang Wang , Ananth Grama , Junyuan Hong

Reinforcement Learning with Human Feedback (RLHF) has become crucial for aligning Large Language Models (LLMs) with human intent. However, existing offline RLHF approaches suffer from overoptimization, where language models degrade by…

Machine Learning · Computer Science 2026-04-20 Sharan Sahu , Martin T. Wells

In this paper, we study offline Reinforcement Learning with Human Feedback (RLHF) where we aim to learn the human's underlying reward and the MDP's optimal policy from a set of trajectories induced by human choices. RLHF is challenging for…

Machine Learning · Computer Science 2023-07-04 Zihao Li , Zhuoran Yang , Mengdi Wang

Reward models (RMs) play a pivotal role in aligning large language models (LLMs) with human preferences. However, traditional RM training, which relies on response pairs tied to specific prompts, struggles to disentangle prompt-driven…

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

Inverse Reinforcement Learning (IRL) and Reinforcement Learning from Human Feedback (RLHF) are pivotal methodologies in reward learning, which involve inferring and shaping the underlying reward function of sequential decision-making…

Machine Learning · Computer Science 2024-10-16 Kihyun Kim , Jiawei Zhang , Asuman Ozdaglar , Pablo A. Parrilo

We study reinforcement learning from human feedback in general Markov decision processes, where agents learn from trajectory-level preference comparisons. A central challenge in this setting is to design algorithms that select informative…

Machine Learning · Computer Science 2025-12-05 Andreas Schlaginhaufen , Reda Ouhamma , Maryam Kamgarpour

Reward modeling is crucial for aligning large language models with human preferences, yet current approaches lack a principled mathematical framework for leveraging ordinal preference data. When human annotators provide graded preferences…

Machine Learning · Computer Science 2026-03-04 Amirhossein Afsharrad , Ruida Zhou , Luca Viano , Sanjay Lall , Mohammad Ghavamzadeh

Reinforcement learning from human or AI feedback (RLHF/RLAIF) for speech-in/speech-out dialogue systems (SDS) remains underexplored, with prior work largely limited to single semantic rewards applied at the utterance level. Such setups…

Computation and Language · Computer Science 2026-01-28 Siddhant Arora , Jinchuan Tian , Jiatong Shi , Hayato Futami , Yosuke Kashiwagi , Emiru Tsunoo , Shinji Watanabe

Language model (LM) post-training (or alignment) involves maximizing a reward function that is derived from preference annotations. Direct Preference Optimization (DPO) is a popular offline alignment method that trains a policy directly on…

Machine Learning · Computer Science 2025-03-04 Adam Fisch , Jacob Eisenstein , Vicky Zayats , Alekh Agarwal , Ahmad Beirami , Chirag Nagpal , Pete Shaw , Jonathan Berant

While Reinforcement Learning from Human Feedback (RLHF) is widely used to align Large Language Models (LLMs) with human preferences, it typically assumes homogeneous preferences across users, overlooking diverse human values and minority…

Computation and Language · Computer Science 2025-10-28 Yijiang River Dong , Tiancheng Hu , Yinhong Liu , Ahmet Üstün , Nigel Collier

A single language model, even when aligned with labelers through reinforcement learning from human feedback (RLHF), may not suit all human preferences. Recent approaches therefore prefer customization, gathering multi-dimensional feedback,…

Machine Learning · Computer Science 2024-08-20 Zhanhui Zhou , Jie Liu , Jing Shao , Xiangyu Yue , Chao Yang , Wanli Ouyang , Yu Qiao

Large language models (LLMs) have demonstrated remarkable performances in various tasks. However, the performance of LLMs heavily depends on the input prompt, which has given rise to a number of recent works on prompt optimization. However,…

Machine Learning · Computer Science 2024-05-28 Xiaoqiang Lin , Zhongxiang Dai , Arun Verma , See-Kiong Ng , Patrick Jaillet , Bryan Kian Hsiang Low

Fine-grained control over large language models (LLMs) remains a significant challenge, hindering their adaptability to diverse user needs. While Reinforcement Learning from Human Feedback (RLHF) shows promise in aligning LLMs, its reliance…

Machine Learning · Computer Science 2024-03-07 Haoxiang Wang , Yong Lin , Wei Xiong , Rui Yang , Shizhe Diao , Shuang Qiu , Han Zhao , Tong Zhang

Preference learning algorithms (e.g., RLHF and DPO) are frequently used to steer LLMs to produce generations that are more preferred by humans, but our understanding of their inner workings is still limited. In this work, we study the…

Machine Learning · Computer Science 2024-11-01 Angelica Chen , Sadhika Malladi , Lily H. Zhang , Xinyi Chen , Qiuyi Zhang , Rajesh Ranganath , Kyunghyun Cho