中文
相关论文

相关论文: Counterfactual Reward Model Training for Bias Miti…

200 篇论文

Reinforcement learning from human feedback (RLHF) is widely used to align large language models (LLMs) with human preferences. However, RLHF-trained reward models often exhibit length bias -- a systematic tendency to favor longer responses…

计算与语言 · 计算机科学 2025-11-18 Hyeonji Kim , Sujeong Oh , Sanghack Lee

Reinforcement learning from human feedback (RLHF) is the mainstream paradigm used to align large language models (LLMs) with human preferences. Yet existing RLHF heavily relies on accurate and informative reward models, which are vulnerable…

计算与语言 · 计算机科学 2024-03-15 Wei Shen , Xiaoying Zhang , Yuanshun Yao , Rui Zheng , Hongyi Guo , Yang Liu

Recent advances in large language models (LLMs) have demonstrated significant progress in performing complex tasks. While Reinforcement Learning from Human Feedback (RLHF) has been effective in aligning LLMs with human preferences, it is…

机器学习 · 计算机科学 2025-05-30 Chaoqi Wang , Zhuokai Zhao , Yibo Jiang , Zhaorun Chen , Chen Zhu , Yuxin Chen , Jiayi Liu , Lizhu Zhang , Xiangjun Fan , Hao Ma , Sinong Wang

Reinforcement Learning from Human Feedback (RLHF) has become a crucial technology for aligning language models with human values and intentions, enabling models to produce more helpful and harmless responses. Reward models are trained as…

A reliable reward model is essential for aligning large language models with human preferences through reinforcement learning from human feedback. However, standard reward models are susceptible to spurious features that are not causally…

机器学习 · 计算机科学 2026-05-19 Yupei Yang , Lin Yang , Wanxi Deng , Lin Qu , Fan Feng , Biwei Huang , Shikui Tu , Lei Xu

Reinforcement learning from human feedback (RLHF) has emerged as a key technique for aligning the output of large language models (LLMs) with human preferences. To learn the reward function, most existing RLHF algorithms use the…

机器学习 · 统计学 2026-02-11 Kai Ye , Hongyi Zhou , Jin Zhu , Francesco Quinzan , Chengchun Shi

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…

人工智能 · 计算机科学 2026-05-11 Tiffany Horter , Andrew Markham , Niki Trigoni , Serena Booth

Reinforcement Learning from Human Feedback (RLHF) is a pivotal technique for aligning large language models (LLMs) with human preferences, yet it is susceptible to reward overoptimization, in which policy models overfit to the reward model,…

Reinforcement learning from human feedback (RLHF) has become a key factor in aligning model behavior with users' goals. However, while humans integrate multiple strategies when making decisions, current RLHF approaches often simplify this…

机器学习 · 计算机科学 2025-06-19 Mingkang Wu , Devin White , Evelyn Rose , Vernon Lawhern , Nicholas R Waytowich , Yongcan Cao

Reinforcement Learning from Human Feedback (RLHF) is a powerful paradigm for aligning foundation models to human values and preferences. However, current RLHF techniques cannot account for the naturally occurring differences in individual…

机器学习 · 计算机科学 2024-08-20 Sriyash Poddar , Yanming Wan , Hamish Ivison , Abhishek Gupta , Natasha Jaques

Reinforcement Learning from Human Feedback (RLHF) enables powerful LLM alignment but can introduce reward hacking - models exploit spurious correlations in proxy rewards without genuine alignment. Compounding this, the objectives…

人工智能 · 计算机科学 2026-02-24 Mohammad Beigi , Ming Jin , Junshan Zhang , Jiaxin Zhang , Qifan Wang , Lifu Huang

Reinforcement Learning with Human Feedback (RLHF) and Reinforcement Learning with Verifiable Rewards (RLVR) are the main RL paradigms used in LLM post-training, each offering distinct advantages. However, RLHF struggles with…

Reinforcement Learning with Human Feedback (RLHF) has emerged as a key paradigm for task-specific fine-tuning of language models using human preference data. While numerous publicly available preference datasets provide pairwise comparisons…

计算与语言 · 计算机科学 2025-11-03 Ashwin Kumar , Yuzi He , Aram H. Markosyan , Bobbie Chern , Imanol Arrieta-Ibarra

Reinforcement Learning with Verifiable Rewards (RLVR) replaces costly human labeling with automated verifiers. To reduce verifier hacking, many RLVR systems binarize rewards to $\{0,1\}$, but imperfect verifiers inevitably introduce…

机器学习 · 计算机科学 2026-05-25 Xin-Qiang Cai , Wei Wang , Feng Liu , Tongliang Liu , Gang Niu , Masashi Sugiyama

Reinforcement learning from human feedback (RLHF) has emerged as a central framework for aligning large language models (LLMs) with human preferences. Despite its practical success, RLHF raises fundamental statistical questions because it…

机器学习 · 统计学 2026-04-06 Pangpang Liu , Chengchun Shi , Will Wei Sun

Recent advances in aligning Large Language Models with human preferences have benefited from larger reward models and better preference data. However, most of these methodologies rely on the accuracy of the reward model. The reward models…

人工智能 · 计算机科学 2024-11-01 Debangshu Banerjee , Aditya Gopalan

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…

机器学习 · 计算机科学 2026-05-29 Zhenyu Sun , Zheng Xu , Ermin Wei

Reinforcement Learning from Human Feedback (RLHF) is a widely used framework for the training of language models. However, the process of using RLHF to develop a language model that is well-aligned presents challenges, especially when it…

计算与语言 · 计算机科学 2024-04-09 Bowen Qin , Duanyu Feng , Xi Yang

Reinforcement Learning from Human Feedback (RLHF) is crucial for aligning large language models with human preferences. While recent research has focused on algorithmic improvements, the importance of prompt-data construction has been…

机器学习 · 计算机科学 2025-04-03 Wei Shen , Guanlin Liu , Zheng Wu , Ruofei Zhu , Qingping Yang , Chao Xin , Yu Yue , Lin Yan

We study estimation and statistical inference for reward models used in aligning large language models (LLMs). A key component of LLM alignment is reinforcement learning from human feedback (RLHF), where humans compare pairs of…

机器学习 · 统计学 2025-12-04 Pangpang Liu , Junwei Lu , Will Wei Sun
‹ 上一页 1 2 3 10 下一页 ›