English
Related papers

Related papers: Investigating Regularization of Self-Play Language…

200 papers

Despite the significant advancements of self-play fine-tuning (SPIN), which can transform a weak large language model (LLM) into a strong one through competitive interactions between models of varying capabilities, it still faces challenges…

Computation and Language · Computer Science 2025-10-14 Yuhao Zhang , Shaoming Duan , Jinhang Su , Chuanyi Liu , Peiyi Han

Reinforcement Learning from Human Feedback (RLHF) has become the standard approach for aligning Large Language Models (LLMs) with human preferences, allowing LLMs to demonstrate remarkable abilities in various tasks. Existing methods work…

Reinforcement learning from human feedback (RLHF) typically assumes a static or non-strategic reward model (RM). In iterative deployment, however, the policy generates the data on which the RM is retrained, creating a feedback loop.…

Machine Learning · Computer Science 2026-05-07 Etienne Gauthier , Francis Bach , Michael I. Jordan

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

Proximal Policy Optimization (PPO) is commonly used in Reinforcement Learning from Human Feedback to align large language models (LLMs) with downstream tasks. This paper investigates the feasibility of using PPO for direct reinforcement…

Computation and Language · Computer Science 2024-10-23 Alexander G. Padula , Dennis J. N. J. Soemers

Reinforcement Learning from Human Feedback (RLHF) leverages a Kullback-Leibler (KL) divergence loss to stabilize training and prevent overfitting. However, in methods such as GRPO, its implementation may be guided by principles from…

Machine Learning · Computer Science 2025-10-07 Kezhao Liu , Jason Klein Liu , Mingtao Chen , Yiming Liu

Aligning generative models with human preference via RLHF typically suffers from overoptimization, where an imperfectly learned reward model can misguide the generative model to output undesired responses. We investigate this problem in a…

Machine Learning · Computer Science 2024-12-05 Zhihan Liu , Miao Lu , Shenao Zhang , Boyi Liu , Hongyi Guo , Yingxiang Yang , Jose Blanchet , Zhaoran Wang

The technique of Reinforcement Learning from Human Feedback (RLHF) is a commonly employed method to improve pre-trained Language Models (LM), enhancing their ability to conform to human preferences. Nevertheless, the current RLHF-based LMs…

Machine Learning · Computer Science 2024-03-27 Han Zhang , Lin Gui , Yuanzhao Zhai , Hui Wang , Yu Lei , Ruifeng Xu

In this article, we investigate the alignment of Large Language Models according to human preferences. We discuss the features of training a Preference Model, which simulates human preferences, and the methods and details we found essential…

Machine Learning · Computer Science 2024-10-03 Alexey Kutalev , Sergei Markoff

Reward models trained on human preference data have been proven to effectively align Large Language Models (LLMs) with human intent within the framework of reinforcement learning from human feedback (RLHF). However, current reward models…

Computation and Language · Computer Science 2024-10-24 Rui Yang , Ruomeng Ding , Yong Lin , Huan Zhang , Tong Zhang

Reinforcement Learning from Human Feedback (RLHF) is a key method for aligning large language models (LLMs) with human preferences. However, current offline alignment approaches like DPO, IPO, and SLiC rely heavily on fixed preference…

Machine Learning · Computer Science 2024-06-25 Mucong Ding , Souradip Chakraborty , Vibhu Agrawal , Zora Che , Alec Koppel , Mengdi Wang , Amrit Bedi , Furong Huang

Reinforcement Learning from Human Feedback (RLHF) aligns language models to human preferences by employing a singular reward model derived from preference data. However, such an approach overlooks the rich diversity of human preferences…

Computation and Language · Computer Science 2024-12-30 Souradip Chakraborty , Jiahao Qiu , Hui Yuan , Alec Koppel , Furong Huang , Dinesh Manocha , Amrit Singh Bedi , Mengdi Wang

Aligning large language models (LLMs) with human preferences has become essential for safe and beneficial AI deployment. While Reinforcement Learning from Human Feedback (RLHF) established the dominant paradigm, a proliferation of…

Artificial Intelligence · Computer Science 2026-01-13 Tarun Raheja , Nilay Pochhi

Reverse-Kullback-Leibler (KL) regularization has emerged to be a predominant technique used to enhance policy optimization in reinforcement learning (RL) and reinforcement learning from human feedback (RLHF), which forces the learned policy…

Machine Learning · Computer Science 2025-02-12 Heyang Zhao , Chenlu Ye , Quanquan Gu , Tong Zhang

We apply preference modeling and reinforcement learning from human feedback (RLHF) to finetune language models to act as helpful and harmless assistants. We find this alignment training improves performance on almost all NLP evaluations,…

Learning from human feedback has been shown to be effective at aligning language models with human preferences. Past work has often relied on Reinforcement Learning from Human Feedback (RLHF), which optimizes the language model using reward…

Computation and Language · Computer Science 2023-05-18 Yao Zhao , Rishabh Joshi , Tianqi Liu , Misha Khalman , Mohammad Saleh , Peter J. Liu

Standard human preference-based alignment methods, such as Reinforcement Learning from Human Feedback (RLHF), are a cornerstone for aligning large language models (LLMs) with human values. However, these methods typically assume that…

Artificial Intelligence · Computer Science 2026-03-02 Xiaoyang Cao , Zelai Xu , Mo Guang , Kaiwen Long , Michiel A. Bakker , Yu Wang , Chao Yu

Reinforcement learning from human feedback (RLHF) has demonstrated remarkable effectiveness in aligning large language models (LLMs) with human preferences. Many existing alignment approaches rely on the Bradley-Terry (BT) model assumption,…

Machine Learning · Computer Science 2025-02-25 Yuheng Zhang , Dian Yu , Tao Ge , Linfeng Song , Zhichen Zeng , Haitao Mi , Nan Jiang , Dong Yu

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

Pre-trained large-scale language models (LLMs) excel at producing coherent articles, yet their outputs may be untruthful, toxic, or fail to align with user expectations. Current approaches focus on using reinforcement learning with human…

Computation and Language · Computer Science 2024-06-06 Dehong Xu , Liang Qiu , Minseok Kim , Faisal Ladhak , Jaeyoung Do