English
Related papers

Related papers: Regularizing Hidden States Enables Learning Genera…

200 papers

We investigate Reinforcement Learning from Human Feedback (RLHF) in the context of a general preference oracle. In particular, we do not assume the existence of a reward function and an oracle preference signal drawn from the Bradley-Terry…

Machine Learning · Computer Science 2024-11-13 Chenlu Ye , Wei Xiong , Yuheng Zhang , Hanze Dong , Nan Jiang , Tong Zhang

To ensure that large language model (LLM) responses are helpful and non-toxic, a reward model trained on human preference data is usually used. LLM responses with high rewards are then selected through best-of-$n$ (BoN) sampling or the LLM…

Machine Learning · Computer Science 2024-07-04 Adam X. Yang , Maxime Robeyns , Thomas Coste , Zhengyan Shi , Jun Wang , Haitham Bou-Ammar , Laurence Aitchison

Reinforcement learning from Human Feedback (RLHF) learns from preference signals, while standard Reinforcement Learning (RL) directly learns from reward signals. Preferences arguably contain less information than rewards, which makes…

Machine Learning · Computer Science 2023-11-07 Yuanhao Wang , Qinghua Liu , Chi Jin

Despite the success of Reinforcement Learning from Human Feedback (RLHF) in aligning language models with human values, reward hacking-or reward over-optimization-remains a major challenge. We identify two key obstacles to its mitigation:…

Machine Learning · Computer Science 2025-10-16 Yuchun Miao , Liang Ding , Sen Zhang , Rong Bao , Lefei Zhang , Dacheng Tao

The reward model has become increasingly important in alignment, assessment, and data construction for large language models (LLMs). Most existing researchers focus on enhancing reward models through data improvements, following the…

Computation and Language · Computer Science 2025-01-09 Shujun Liu , Xiaoyu Shen , Yuhang Lai , Siyuan Wang , Shengbin Yue , Zengfeng Huang , Xuanjing Huang , Zhongyu Wei

Reinforcement learning from human feedback (RLHF) is an effective method for aligning large language models (LLMs) with human values. However, reward over-optimization remains an open challenge leading to discrepancies between the…

Machine Learning · Computer Science 2025-03-25 Juntao Dai , Taiye Chen , Yaodong Yang , Qian Zheng , Gang Pan

Reinforcement Learning from Human Feedback (RLHF) aligns Large Language Models (LLMs) with human preferences, yet the underlying reward signals they internalize remain hidden, posing a critical challenge for interpretability and safety.…

Machine Learning · Computer Science 2026-01-21 Nyal Patel , Matthieu Bou , Arjun Jagota , Satyapriya Krishna , Sonali Parbhoo

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,…

The alignment of Large Language Models (LLMs) is critically dependent on reward models trained on costly human preference data. While recent work explores bypassing this cost with AI feedback, these methods often lack a rigorous theoretical…

Computation and Language · Computer Science 2025-07-01 Yi-Chen Li , Tian Xu , Yang Yu , Xuqin Zhang , Xiong-Hui Chen , Zhongxiang Ling , Ningjing Chao , Lei Yuan , Zhi-Hua Zhou

Preference alignment in Large Language Models (LLMs) has significantly improved their ability to adhere to human instructions and intentions. However, existing direct alignment algorithms primarily focus on relative preferences and often…

Machine Learning · Computer Science 2025-05-13 Shenao Zhang , Zhihan Liu , Boyi Liu , Yufeng Zhang , Yingxiang Yang , Yongfei Liu , Liyu Chen , Tao Sun , Zhaoran Wang

Reinforcement learning from human feedback (RLHF) aligns large language models (LLMs) by encouraging their generations to have high rewards, using a reward model trained on human preferences. To prevent the forgetting of pre-trained…

Re-inforcement learning from human feedback (RLHF) has been effective in the task of AI alignment. However, one of the key assumptions of RLHF is that the annotators (referred to as workers from here on out) have a homogeneous response…

Human-Computer Interaction · Computer Science 2026-01-29 Sarvesh Shashidhar , Abhishek Mishra , Madhav Kotecha

Reinforcement Learning from Human Feedback (RLHF) is a pivotal technique that aligns language models closely with human-centric values. The initial phase of RLHF involves learning human values using a reward model from ranking data. It is…

Machine Learning · Computer Science 2024-01-30 Banghua Zhu , Michael I. Jordan , Jiantao Jiao

Reinforcement Learning from Human Feedback has become the standard paradigm for language model alignment, where reward models directly determine alignment effectiveness. In this work, we focus on how to evaluate the generalizability of…

Computation and Language · Computer Science 2026-05-05 Yangyang Zhou , Yi-Chen Li

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

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

While reinforcement learning (RL) demonstrated remarkable success in enhancing the reasoning capabilities of language models, the training dynamics of RL in LLMs remain unclear. In this work, we provide an explanation of the RL training…

Machine Learning · Computer Science 2025-09-30 Xingwu Chen , Tianle Li , Difan Zou

Reinforcement Learning from Human Feedback (RLHF) has greatly improved the performance of modern Large Language Models (LLMs). The RLHF process is resource-intensive and technically challenging, generally requiring a large collection of…

Reinforcement Learning with Verifiable reward (RLVR) on preference data has become the mainstream approach for training Generative Reward Models (GRMs). Typically in pairwise rewarding tasks, GRMs generate reasoning chains ending with…

Computation and Language · Computer Science 2026-05-04 Zongqi Wang , Rui Wang , Yuchuan Wu , Yiyao Yu , Pinyi Zhang , Shaoning Sun , Yujiu Yang , Yongbin Li

Large language models (LLMs) are often sycophantic, prioritizing agreement with their users over accurate or objective statements. This problematic behavior becomes more pronounced during reinforcement learning from human feedback (RLHF),…

Artificial Intelligence · Computer Science 2024-12-03 Henry Papadatos , Rachel Freedman
‹ Prev 1 4 5 6 7 8 10 Next ›