English
Related papers

Related papers: Towards Reliable Alignment: Uncertainty-aware RLHF

200 papers

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 success of AI assistants based on language models (LLMs) hinges crucially on Reinforcement Learning from Human Feedback (RLHF), which enables the generation of responses more aligned with human preferences. As universal AI assistants,…

Machine Learning · Computer Science 2023-12-27 Rui Zheng , Wei Shen , Yuan Hua , Wenbin Lai , Shihan Dou , Yuhao Zhou , Zhiheng Xi , Xiao Wang , Haoran Huang , Tao Gui , Qi Zhang , Xuanjing Huang

Large Language Models (LLMs) have made substantial strides in structured tasks through Reinforcement Learning (RL), demonstrating proficiency in mathematical reasoning and code generation. However, applying RL in broader domains like…

Computation and Language · Computer Science 2025-02-10 Hao Sun , Yunyi Shen , Jean-Francois Ton , Mihaela van der Schaar

Reinforcement Learning from Human Feedback (RLHF) has advanced alignment capabilities significantly but remains hindered by two core challenges: \textbf{reward hacking} and \textbf{stable optimization}. Current solutions independently…

Machine Learning · Computer Science 2026-02-13 Li He , Qiang Qu , He Zhao , Stephen Wan , Dadong Wang , Lina Yao , Tongliang Liu

The burgeoning field of autonomous driving necessitates the seamless integration of autonomous vehicles (AVs) with human-driven vehicles, calling for more predictable AV behavior and enhanced interaction with human drivers. Human-like…

Computational Engineering, Finance, and Science · Computer Science 2024-08-09 Yuting Wang , Lu Liu , Maonan Wang , Xi Xiong

Large Multimodal Models (LMM) are built across modalities and the misalignment between two modalities can result in "hallucination", generating textual outputs that are not grounded by the multimodal information in context. To address the…

Computer Vision and Pattern Recognition · Computer Science 2023-09-27 Zhiqing Sun , Sheng Shen , Shengcao Cao , Haotian Liu , Chunyuan Li , Yikang Shen , Chuang Gan , Liang-Yan Gui , Yu-Xiong Wang , Yiming Yang , Kurt Keutzer , Trevor Darrell

The reward model for Reinforcement Learning from Human Feedback (RLHF) has proven effective in fine-tuning Large Language Models (LLMs). Notably, collecting human feedback for RLHF can be resource-intensive and lead to scalability issues…

Computation and Language · Computer Science 2024-07-09 Jinghan Zhang , Xiting Wang , Yiqiao Jin , Changyu Chen , Xinhao Zhang , Kunpeng Liu

Existing alignment methods share a common topology of information flow, where reward information is collected from humans, modeled with preference learning, and used to tune language models. However, this shared topology has not been…

Machine Learning · Computer Science 2025-05-29 Tianyi Qiu , Fanzhi Zeng , Jiaming Ji , Dong Yan , Kaile Wang , Jiayi Zhou , Yang Han , Josef Dai , Xuehai Pan , Yaodong Yang

Reinforcement Learning from Human Feedback relies on reward models to align large language models with human preferences. However, RLHF often suffers from reward hacking, wherein policy learning exploits flaws in the trained reward model to…

Machine Learning · Computer Science 2025-05-20 Kangwen Zhao , Jianfeng Cai , Jinhua Zhu , Ruopei Sun , Dongyun Xue , Wengang Zhou , Li Li , Houqiang Li

Reinforcement Learning with Verifiable reward (RLVR) on preference data has become the mainstream approach for training Generative Reward Models (GRMs). Typically in pairwise rewarding tasks, GRMs generate reasoning chains ending with…

Computation and Language · Computer Science 2026-05-04 Zongqi Wang , Rui Wang , Yuchuan Wu , Yiyao Yu , Pinyi Zhang , Shaoning Sun , Yujiu Yang , Yongbin Li

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…

Machine Learning · Computer Science 2025-04-03 Wei Shen , Guanlin Liu , Zheng Wu , Ruofei Zhu , Qingping Yang , Chao Xin , Yu Yue , Lin Yan

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

Finetuning language models with reinforcement learning (RL), e.g. from human feedback (HF), is a prominent method for alignment. But optimizing against a reward model can improve on reward while degrading performance in other areas, a…

Computation and Language · Computer Science 2023-12-14 Michael Noukhovitch , Samuel Lavoie , Florian Strub , Aaron Courville

We introduce ALaRM, the first framework modeling hierarchical rewards in reinforcement learning from human feedback (RLHF), which is designed to enhance the alignment of large language models (LLMs) with human preferences. The framework…

Computation and Language · Computer Science 2024-03-19 Yuhang Lai , Siyuan Wang , Shujun Liu , Xuanjing Huang , Zhongyu Wei

Reinforcement Learning from Human Feedback (RLHF) is currently the most widely used method to align large language models (LLMs) with human preferences. Existing RLHF methods can be roughly categorized as either reward-based or reward-free.…

Computation and Language · Computer Science 2024-10-11 Shusheng Xu , Wei Fu , Jiaxuan Gao , Wenjie Ye , Weilin Liu , Zhiyu Mei , Guangju Wang , Chao Yu , Yi Wu

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 emerged as a reliable approach to aligning large language models (LLMs) to human preferences. Among the plethora of RLHF techniques, proximal policy optimization (PPO) is of the most…

Computation and Language · Computer Science 2023-11-06 Banghua Zhu , Hiteshi Sharma , Felipe Vieira Frujeri , Shi Dong , Chenguang Zhu , Michael I. Jordan , Jiantao Jiao

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

Training language models via reinforcement learning often relies on imperfect proxy rewards, since ground truth rewards that precisely define the intended behavior are rarely available. Standard metrics for assessing the quality of proxy…

Machine Learning · Computer Science 2026-04-29 Shuning Shang , Hubert Strauss , Stanley Wei , Sanjeev Arora , Noam Razin

We provide a theoretical framework for Reinforcement Learning with Human Feedback (RLHF). Our analysis shows that when the true reward function is linear, the widely used maximum likelihood estimator (MLE) converges under both the…

Machine Learning · Computer Science 2024-02-09 Banghua Zhu , Jiantao Jiao , Michael I. Jordan