English
Related papers

Related papers: Catastrophic Goodhart: regularizing RLHF with KL d…

200 papers

Alignment via reinforcement learning from human feedback (RLHF) has become the dominant paradigm for controlling the quality of outputs from large language models (LLMs). However, existing theories do not provide strong justification for…

Machine Learning · Computer Science 2026-05-19 Jihun Yun , Juno Kim , Jongho Park , Junhyuck Kim , Jongha Jon Ryu , Jaewoong Cho , Kwang-Sung Jun

Reinforcement learning from human feedback (RLHF) is a crucial technique in aligning large language models (LLMs) with human preferences, ensuring these LLMs behave in beneficial and comprehensible ways to users. However, a longstanding…

Artificial Intelligence · Computer Science 2024-03-27 Feiteng Fang , Liang Zhu , Min Yang , Xi Feng , Jinchang Hou , Qixuan Zhao , Chengming Li , Xiping Hu , Ruifeng Xu

Reinforcement learning (RL), a common tool in decision making, learns control policies from various experiences based on the associated cumulative return/rewards without treating them differently. Humans, on the contrary, often learn to…

Machine Learning · Computer Science 2025-11-25 Mingkang Wu , Devin White , Vernon Lawhern , Nicholas R. Waytowich , Yongcan Cao

Reinforcement Learning from Human Feedback (RLHF) is commonly utilized to improve the alignment of Large Language Models (LLMs) with human preferences. Given the evolving nature of human preferences, continual alignment becomes more crucial…

Machine Learning · Computer Science 2024-12-24 Han Zhang , Lin Gui , Yu Lei , Yuanzhao Zhai , Yehong Zhang , Yulan He , Hui Wang , Yue Yu , Kam-Fai Wong , Bin Liang , Ruifeng Xu

Reinforcement learning from human feedback (RLHF) has become a cornerstone for aligning large language models with human preferences. However, the heterogeneity of human feedback, driven by diverse individual contexts and preferences, poses…

Machine Learning · Statistics 2026-03-05 Seong Jin Lee , Will Wei Sun , Yufeng Liu

While large-scale unsupervised language models (LMs) learn broad world knowledge and some reasoning skills, achieving precise control of their behavior is difficult due to the completely unsupervised nature of their training. Existing…

Machine Learning · Computer Science 2024-07-31 Rafael Rafailov , Archit Sharma , Eric Mitchell , Stefano Ermon , Christopher D. Manning , Chelsea Finn

Reinforcement Learning from Human Feedback (RLHF) is central in aligning large language models (LLMs) with human values and expectations. However, the process remains susceptible to governance challenges, including evaluator bias,…

Computers and Society · Computer Science 2025-04-22 Dana Alsagheer , Abdulrahman Kamal , Mohammad Kamal , Weidong Shi

We study reinforcement learning (RL) problems in which agents observe the reward or transition realizations at their current state before deciding which action to take. Such observations are available in many applications, including…

Machine Learning · Computer Science 2024-10-22 Nadav Merlis

Large Language Models (LLMs) have revolutionized natural language processing, yet aligning these models with human values and preferences using RLHF remains a significant challenge. This challenge is characterized by various instabilities,…

Computation and Language · Computer Science 2023-09-20 Baolin Peng , Linfeng Song , Ye Tian , Lifeng Jin , Haitao Mi , Dong Yu

In real-world scenarios, where knowledge distributions exhibit long-tail. Humans manage to master knowledge uniformly across imbalanced distributions, a feat attributed to their diligent practices of reviewing, summarizing, and correcting…

Computer Vision and Pattern Recognition · Computer Science 2024-09-16 Qihao Zhao , Yalun Dai , Shen Lin , Wei Hu , Fan Zhang , Jun Liu

Diffusion models have revolutionized generative modeling in continuous domains like image, audio, and video synthesis. However, their iterative sampling process leads to slow generation and inefficient training, challenges that are further…

Machine Learning · Computer Science 2025-03-11 Shivanshu Shekhar , Tong Zhang

We study the tail behavior of regret in stochastic multi-armed bandits for algorithms that are asymptotically optimal in expectation. While minimizing expected regret is the classical objective, recent work shows that even such algorithms…

Information Theory · Computer Science 2026-04-17 Subhodip Panda , Shubhada Agrawal

Goal-conditioned reinforcement learning (RL) concerns the problem of training an agent to maximize the probability of reaching target goal states. This paper presents an analysis of the goal-conditioned setting based on optimal control. In…

Machine Learning · Computer Science 2026-05-15 Nathan P. Lawrence , Ali Mesbah

Accurately aligning large language models (LLMs) with human preferences is crucial for informing fair, economically sound, and statistically efficient decision-making processes. However, we argue that the predominant approach for aligning…

Machine Learning · Statistics 2025-08-26 Jiancong Xiao , Ziniu Li , Xingyu Xie , Emily Getzen , Cong Fang , Qi Long , Weijie J. Su

Reinforcement learning from human feedback (RLHF) has been widely adopted to align language models (LMs) with human preference. Prior RLHF works typically take a bandit formulation, which, though intuitive, ignores the sequential nature of…

Computation and Language · Computer Science 2025-01-07 Yueqin Yin , Shentao Yang , Yujia Xie , Ziyi Yang , Yuting Sun , Hany Awadalla , Weizhu Chen , Mingyuan Zhou

Reinforcement Learning from Human Feedback (RLHF) is crucial for aligning Large Language Models (LLMs) with human values. However, RLHF has been continuously challenged by its high complexity in implementation and computation consumption,…

Machine Learning · Computer Science 2026-03-24 Yuhao Du , Zhuo Li , Pengyu Cheng , Zhihong Chen , Yuejiao Xie , Xiang Wan , Anningzhe Gao

Faithfulness, expressiveness, and elegance is the constant pursuit in machine translation. However, traditional metrics like \textit{BLEU} do not strictly align with human preference of translation quality. In this paper, we explore…

Computation and Language · Computer Science 2024-02-28 Nuo Xu , Jun Zhao , Can Zu , Sixian Li , Lu Chen , Zhihao Zhang , Rui Zheng , Shihan Dou , Wenjuan Qin , Tao Gui , Qi Zhang , Xuanjing Huang

Large language models are typically aligned with human preferences by optimizing $\textit{reward models}$ (RMs) fitted to human feedback. However, human preferences are multi-faceted, and it is increasingly common to derive reward from a…

Language model (LM) alignment improves model outputs to reflect human preferences while preserving the capabilities of the base model. The most common alignment approaches are (i) reinforcement learning, which maximizes the expected reward…

Machine Learning · Computer Science 2026-05-11 Lucas Monteiro Paes , Natalie Mackraz , Barry-John Theobald , Federico Danieli

Existing alignment methods directly use the reward model learned from user preference data to optimize an LLM policy, subject to KL regularization with respect to the base policy. This practice is suboptimal for maximizing user's utility…

Machine Learning · Computer Science 2026-02-04 Haichuan Wang , Tao Lin , Lingkai Kong , Ce Li , Hezi Jiang , Milind Tambe