English
Related papers

Related papers: Aligning Crowd Feedback via Distributional Prefere…

200 papers

Reward model (RM) plays a pivotal role in reinforcement learning with human feedback (RLHF) for aligning large language models (LLMs). However, classical RMs trained on human preferences are vulnerable to reward hacking and generalize…

Machine Learning · Computer Science 2025-10-24 Zhenghao Xu , Qin Lu , Qingru Zhang , Liang Qiu , Ilgee Hong , Changlong Yu , Wenlin Yao , Yao Liu , Haoming Jiang , Lihong Li , Hyokun Yun , Tuo Zhao

Reward inference (learning a reward model from human preferences) is a critical intermediate step in the Reinforcement Learning from Human Feedback (RLHF) pipeline for fine-tuning Large Language Models (LLMs). In practice, RLHF faces…

Machine Learning · Computer Science 2025-03-04 Qining Zhang , Lei Ying

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…

Preference optimization is widely used to align large language models (LLMs) with human preferences. However, many margin-based methods also suppress the chosen response when they try to suppress the rejected one, and there is no general…

Machine Learning · Computer Science 2026-05-04 Wei Chen , Yubing Wu , Junmei Yang , Delu Zeng , Qibin Zhao , John Paisley , Min Chen , Zhou Wang

Multimodal large language models (MLLMs) struggle with numerical regression under long-tailed target distributions. Token-level supervised fine-tuning (SFT) and point-wise regression rewards bias learning toward high-density regions,…

Computation and Language · Computer Science 2026-05-12 Yao Du , Shanshan Song , Xiaomeng Li

Offline imitation learning (offline IL) enables training effective policies without requiring explicit reward annotations. Recent approaches attempt to estimate rewards for unlabeled datasets using a small set of expert demonstrations.…

Machine Learning · Computer Science 2025-11-19 Shengjie Sun , Jiafei Lyu , Runze Liu , Mengbei Yan , Bo Liu , Deheng Ye , Xiu Li

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…

Computation and Language · Computer Science 2024-03-15 Wei Shen , Xiaoying Zhang , Yuanshun Yao , Rui Zheng , Hongyi Guo , Yang Liu

The alignment of large language models (LLMs) with human values increasingly relies on using other LLMs as automated judges, or ``autoraters''. However, their reliability is limited by a foundational issue: they are trained on discrete…

Large language models can predict real-valued quantities from heterogeneous inputs such as text, code, and molecular strings, but most training objectives score each decoded floating-point number independently, improving point estimates…

Machine Learning · Computer Science 2026-05-21 Jungsoo Park , Hyungjoo Chae , Ethan Mendes , Jay DeYoung , Varsha Kishore , Wei Xu , Alan Ritter

Reinforcement learning from human feedback (RLHF) is a popular strategy for aligning large language models (LLMs) with desired behaviors. Reward modeling is a crucial step in RLHF. However, collecting paired preference data for training…

Computation and Language · Computer Science 2024-10-08 Tzu-Han Lin , Chen-An Li , Hung-yi Lee , Yun-Nung Chen

Pre-trained large-scale language models (LLMs) excel at producing coherent articles, yet their outputs may be untruthful, toxic, or fail to align with user expectations. Current approaches focus on using reinforcement learning with human…

Computation and Language · Computer Science 2024-06-06 Dehong Xu , Liang Qiu , Minseok Kim , Faisal Ladhak , Jaeyoung Do

Recent advances in Large Language Models (LLMs) highlight the need to align their behaviors with human values. A critical, yet understudied, issue is the potential divergence between an LLM's stated preferences (its reported alignment with…

Artificial Intelligence · Computer Science 2025-06-03 Zhuojun Gu , Quan Wang , Shuchu Han

Reinforcement learning from human feedback (RLHF) is a critical technique for training large language models. However, conventional reward models based on the Bradley-Terry model (BTRM) often suffer from overconfidence when faced with…

Machine Learning · Computer Science 2025-05-19 Wangtao Sun , Xiang Cheng , Xing Yu , Haotian Xu , Zhao Yang , Shizhu He , Jun Zhao , Kang Liu

Reward models (RMs) are a core component in the post-training of large language models (LLMs), serving as proxies for human preference evaluation and guiding model alignment. However, training reliable RMs under limited resources remains…

Artificial Intelligence · Computer Science 2025-11-12 Dengcan Liu , Jiahao Li , Zheren Fu , Yi Tu , Jiajun Li , Zhendong Mao , Yongdong Zhang

We study an LLM fine-tuning task for designing reward functions for sequential resource allocation problems in public health, guided by human preferences expressed in natural language. This setting presents a challenging testbed for…

Machine Learning · Computer Science 2025-11-19 Cheol Woo Kim , Shresth Verma , Mauricio Tec , Milind Tambe

In reinforcement learning (RL), agents continually interact with the environment and use the feedback to refine their behavior. To guide policy optimization, reward models are introduced as proxies of the desired objectives, such that when…

Machine Learning · Computer Science 2025-06-19 Rui Yu , Shenghua Wan , Yucen Wang , Chen-Xiao Gao , Le Gan , Zongzhang Zhang , De-Chuan Zhan

Reward Models (RMs) are critical components in the Reinforcement Learning from Human Feedback (RLHF) pipeline, directly determining the alignment quality of Large Language Models (LLMs). Recently, Generative Reward Models (GRMs) have…

Artificial Intelligence · Computer Science 2026-04-21 Kai Qin , Liangxin Liu , Yu Liang , Longzheng Wang , Yan Wang , Yueyang Zhang , Long Xia , Zhiyuan Sun , Houde Liu , Daiting Shi

Large language models (LLMs) are designed to perform a wide range of tasks. To improve their ability to solve complex problems requiring multi-step reasoning, recent research leverages process reward modeling to provide fine-grained…

Computation and Language · Computer Science 2025-09-29 Weixuan Wang , Minghao Wu , Barry Haddow , Alexandra Birch

Aligning large language models (LLMs) with human preferences is critical to recent advances in generative artificial intelligence. Reinforcement learning from human feedback (RLHF) is widely applied to achieve this objective. A key step in…

Machine Learning · Statistics 2025-01-03 Pangpang Liu , Chengchun Shi , Will Wei Sun

Preference-based reinforcement learning (PbRL) shows promise in aligning robot behaviors with human preferences, but its success depends heavily on the accurate modeling of human preferences through reward models. Most methods adopt…

Robotics · Computer Science 2025-03-12 Dezhong Zhao , Ruiqi Wang , Dayoon Suh , Taehyeon Kim , Ziqin Yuan , Byung-Cheol Min , Guohua Chen
‹ Prev 1 8 9 10 Next ›