English
Related papers

Related papers: Learning from Failures: Understanding LLM Alignmen…

200 papers

Existing algorithms for reinforcement learning from human feedback (RLHF) can incentivize responses at odds with preferences because they are based on models that assume independence of irrelevant alternatives (IIA). The perverse incentives…

Machine Learning · Computer Science 2024-02-02 Wanqiao Xu , Shi Dong , Xiuyuan Lu , Grace Lam , Zheng Wen , Benjamin Van Roy

The correct specification of reward models is a well-known challenge in reinforcement learning. Hand-crafted reward functions often lead to inefficient or suboptimal policies and may not be aligned with user values. Reinforcement learning…

Artificial Intelligence · Computer Science 2024-10-24 Muhan Lin , Shuyang Shi , Yue Guo , Behdad Chalaki , Vaishnav Tadiparthi , Ehsan Moradi Pari , Simon Stepputtis , Joseph Campbell , Katia Sycara

Reinforcement learning from human feedback (RLHF) is a prevalent approach to align AI systems with human values by learning rewards from human preference data. Due to various reasons, however, such data typically takes the form of rankings…

Machine Learning · Computer Science 2024-06-06 Ilgee Hong , Zichong Li , Alexander Bukharin , Yixiao Li , Haoming Jiang , Tianbao Yang , Tuo Zhao

This paper critically evaluates the attempts to align Artificial Intelligence (AI) systems, especially Large Language Models (LLMs), with human values and intentions through Reinforcement Learning from Feedback (RLxF) methods, involving…

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

The goal of inverse reinforcement learning (IRL) is to infer a reward function that explains the behavior of an agent performing a task. The assumption that most approaches make is that the demonstrated behavior is near-optimal. In many…

Machine Learning · Computer Science 2020-11-20 Luis Haug , Ivan Ovinnikov , Eugene Bykovets

Reinforcement Learning from Human Feedback (RLHF) is an effective approach for aligning language models to human preferences. Central to RLHF is learning a reward function for scoring human preferences. Two main approaches for learning a…

Fine-tuning large language models (LLMs) to align with user preferences is challenging due to the high cost of quality human annotations in Reinforcement Learning from Human Feedback (RLHF) and the generalizability limitations of AI…

Reinforcement Learning from Human Feedback (RLHF) is a methodology that aligns agent behavior with human preferences by integrating user feedback into the agent's training process. This paper introduces a framework that guides agent…

Artificial Intelligence · Computer Science 2026-02-10 Julia Santaniello , Matthew Russell , Benson Jiang , Donatello Sassaroli , Robert Jacob , Jivko Sinapov

ChatGLM is a free-to-use AI service powered by the ChatGLM family of large language models (LLMs). In this paper, we present the ChatGLM-RLHF pipeline -- a reinforcement learning from human feedback (RLHF) system -- designed to enhance…

Computation and Language · Computer Science 2024-04-04 Zhenyu Hou , Yilin Niu , Zhengxiao Du , Xiaohan Zhang , Xiao Liu , Aohan Zeng , Qinkai Zheng , Minlie Huang , Hongning Wang , Jie Tang , Yuxiao Dong

As AI systems become increasingly autonomous, aligning their decision-making to human preferences is essential. In domains like autonomous driving or robotics, it is impossible to write down the reward function representing these…

Machine Learning · Computer Science 2025-01-03 Ondrej Bajgar , Sid William Gould , Rohan Narayan Langford Mitta , Jonathon Liu , Oliver Newcombe , Jack Golden

Inverse reinforcement learning (IRL) aims to infer an agent's preferences (represented as a reward function $R$) from their behaviour (represented as a policy $\pi$). To do this, we need a behavioural model of how $\pi$ relates to $R$. In…

Machine Learning · Computer Science 2024-03-12 Joar Skalse , Alessandro Abate

Inverse reinforcement learning (IRL) is the problem of inferring the reward function of an agent, given its policy or observed behavior. Analogous to RL, IRL is perceived both as a problem and as a class of methods. By categorically…

Machine Learning · Computer Science 2020-11-19 Saurabh Arora , Prashant Doshi

In Reinforcement Learning from Human Feedback (RLHF), it is crucial to learn suitable reward models from human feedback to align large language models (LLMs) with human intentions. However, human feedback can often be noisy, inconsistent,…

Artificial Intelligence · Computer Science 2025-09-03 Taywon Min , Haeone Lee , Yongchan Kwon , Kimin Lee

The objectives that Large Language Models (LLMs) implicitly optimize remain dangerously opaque, making trustworthy alignment and auditing a grand challenge. While Inverse Reinforcement Learning (IRL) can infer reward functions from…

Machine Learning · Computer Science 2025-10-09 Matthieu Bou , Nyal Patel , Arjun Jagota , Satyapriya Krishna , Sonali Parbhoo

Reinforcement learning has shown remarkable performance in aligning language models with human preferences, leading to the rise of attention towards developing RLHF platforms. These platforms enable users to fine-tune models without…

Machine Learning · Computer Science 2025-03-06 Erfan Entezami , Ali Naseh

Reinforcement learning from human feedback (RLHF) has become an important technical and storytelling tool to deploy the latest machine learning systems. In this book, we hope to give a gentle introduction to the core methods for people with…

Machine Learning · Computer Science 2026-05-12 Nathan Lambert

Reinforcement Learning from Human Feedback (RLHF) has shown remarkable success in aligning Large Language Models (LLMs) with human preferences. Traditional RLHF methods rely on a fixed dataset, which often suffers from limited coverage. To…

Machine Learning · Computer Science 2025-10-28 Long-Fei Li , Yu-Yang Qian , Peng Zhao , Zhi-Hua Zhou

Aligning Large Language Models (LLMs) is crucial for enhancing their safety and utility. However, existing methods, primarily based on preference datasets, face challenges such as noisy labels, high annotation costs, and privacy concerns.…

Machine Learning · Computer Science 2025-01-28 Hao Sun , Mihaela van der Schaar

This paper studies reinforcement learning from human feedback (RLHF) for aligning large language models with human preferences. While RLHF has demonstrated promising results, many algorithms are highly sensitive to misspecifications in the…

Machine Learning · Computer Science 2025-10-30 Erhan Xu , Kai Ye , Hongyi Zhou , Luhan Zhu , Francesco Quinzan , Chengchun Shi