English
Related papers

Related papers: Rule Based Rewards for Language Model Safety

200 papers

Designing effective reward functions is crucial to training reinforcement learning (RL) algorithms. However, this design is non-trivial, even for domain experts, due to the subjective nature of certain tasks that are hard to quantify…

Neural and Evolutionary Computing · Computer Science 2025-05-26 Rishi Hazra , Alkis Sygkounas , Andreas Persson , Amy Loutfi , Pedro Zuidberg Dos Martires

One of the key challenges in current Reinforcement Learning (RL)-based Automated Driving (AD) agents is achieving flexible, precise, and human-like behavior cost-effectively. This paper introduces an innovative approach that uses large…

Artificial Intelligence · Computer Science 2024-12-30 Ziqi Zhou , Jingyue Zhang , Jingyuan Zhang , Yangfan He , Boyue Wang , Tianyu Shi , Alaa Khamis

Reward models are critical in techniques like Reinforcement Learning from Human Feedback (RLHF) and Inference Scaling Laws, where they guide language model alignment and select optimal responses. Despite their importance, existing reward…

Computation and Language · Computer Science 2024-10-22 Yantao Liu , Zijun Yao , Rui Min , Yixin Cao , Lei Hou , Juanzi Li

Reinforcement learning with human feedback for aligning large language models (LLMs) trains a reward model typically using ranking loss with comparison pairs.However, the training procedure suffers from an inherent problem: the uncontrolled…

Computation and Language · Computer Science 2024-09-19 Hang Zhou , Chenglong Wang , Yimin Hu , Tong Xiao , Chunliang Zhang , Jingbo Zhu

Reinforcement learning (RL) often struggles with reward misalignment, where agents optimize given rewards but fail to exhibit the desired behaviors. This arises when the reward function incentivizes proxy behaviors misaligned with the true…

Machine Learning · Computer Science 2025-09-19 Mohammad Saif Nazir , Chayan Banerjee

Reward models (RM) capture the values and preferences of humans and play a central role in Reinforcement Learning with Human Feedback (RLHF) to align pretrained large language models (LLMs). Traditionally, training these models relies on…

Machine Learning · Computer Science 2024-09-12 Yifei He , Haoxiang Wang , Ziyan Jiang , Alexandros Papangelis , Han Zhao

Offline Preference-based Reinforcement Learning (PbRL) learns rewards and policies aligned with human preferences without the need for extensive reward engineering and direct interaction with human annotators. However, ensuring safety…

Artificial Intelligence · Computer Science 2025-12-24 Ze Gong , Pradeep Varakantham , Akshat Kumar

Preference-based Reinforcement Learning (PbRL) is a paradigm in which an RL agent learns to optimize a task using pair-wise preference-based feedback over trajectories, rather than explicit reward signals. While PbRL has demonstrated…

Machine Learning · Computer Science 2024-04-18 Wenhao Zhan , Masatoshi Uehara , Wen Sun , Jason D. Lee

Reinforcement learning from human feedback usually models preferences using a reward function that does not distinguish between people. We argue that this is unlikely to be a good design choice in contexts with high potential for…

Reward models (RMs), which are central to existing post-training methods, aim to align LLM outputs with human values by providing feedback signals during fine-tuning. However, existing RMs struggle to capture nuanced, user-specific…

Machine Learning · Computer Science 2025-08-21 Mengdi Li , Guanqiao Chen , Xufeng Zhao , Haochen Wen , Shu Yang , Di Wang

As Large Language Models (LLMs) continue to progress toward more advanced forms of intelligence, Reinforcement Learning from Human Feedback (RLHF) is increasingly seen as a key pathway toward achieving Artificial General Intelligence (AGI).…

Machine Learning · Computer Science 2024-10-17 Yuzi Yan , Xingzhou Lou , Jialian Li , Yiping Zhang , Jian Xie , Chao Yu , Yu Wang , Dong Yan , Yuan Shen

Reinforcement Learning (RL)-based recommender systems have demonstrated promising performance in meeting user expectations by learning to make accurate next-item recommendations from historical user-item interactions. However, existing…

Information Retrieval · Computer Science 2024-03-26 Jie Wang , Alexandros Karatzoglou , Ioannis Arapakis , Joemon M. Jose

Preference-based Reinforcement Learning (PbRL) circumvents the need for reward engineering by harnessing human preferences as the reward signal. However, current PbRL methods excessively depend on high-quality feedback from domain experts,…

Machine Learning · Computer Science 2024-10-29 Jie Cheng , Gang Xiong , Xingyuan Dai , Qinghai Miao , Yisheng Lv , Fei-Yue Wang

This paper explores multiple optimization methods to improve the performance of rating-based reinforcement learning (RbRL). RbRL, a method based on the idea of human ratings, has been developed to infer reward functions in reward-free…

Machine Learning · Computer Science 2025-01-15 Evelyn Rose , Devin White , Mingkang Wu , Vernon Lawhern , Nicholas R. Waytowich , Yongcan Cao

Reinforcement Learning from Human Feedback (RLHF) can reveal implicit objectives such as safety considerations that go beyond task completion. In this work, we focus on the common safety criteria embedded in crowd preference datasets, where…

Artificial Intelligence · Computer Science 2026-05-22 Qian Lin , Daniel S. Brown

Preference-based reinforcement learning (RL) has emerged as a new field in robot learning, where humans play a pivotal role in shaping robot behavior by expressing preferences on different sequences of state-action pairs. However,…

Robotics · Computer Science 2024-02-26 Simon Holk , Daniel Marta , Iolanda Leite

Conveying complex objectives to reinforcement learning (RL) agents can often be difficult, involving meticulous design of reward functions that are sufficiently informative yet easy enough to provide. Human-in-the-loop RL methods allow…

Machine Learning · Computer Science 2021-06-10 Kimin Lee , Laura Smith , Pieter Abbeel

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 (RL) has become a predominant technique to align language models (LMs) with human preferences or promote outputs which are deemed to be desirable by a given reward function. Standard RL approaches optimize average…

Machine Learning · Computer Science 2025-10-27 Stephen Zhao , Aidan Li , Rob Brekelmans , Roger Grosse

Alignment of Large Language Models (LLMs) aims to align outputs with human preferences, and personalized alignment further adapts models to individual users. This relies on personalized reward models that capture user-specific preferences…

Computation and Language · Computer Science 2026-04-21 Hongru Cai , Yongqi Li , Tiezheng Yu , Fengbin Zhu , Wenjie Wang , Fuli Feng , Wenjie Li