English
Related papers

Related papers: Simultaneous Multi-objective Alignment Across Veri…

200 papers

Reinforcement learning (RL) can align language models with non-differentiable reward signals, such as human preferences. However, a major challenge arises from the sparsity of these reward signals - typically, there is only a single reward…

Computation and Language · Computer Science 2024-02-20 Meng Cao , Lei Shu , Lei Yu , Yun Zhu , Nevan Wichers , Yinxiao Liu , Lei Meng

Ensuring AI models align with human values is essential for their safety and functionality. Reinforcement learning from human feedback (RLHF) leverages human preferences to achieve this alignment. However, when preferences are sourced from…

Machine Learning · Computer Science 2025-02-10 Ryan Bahlous-Boldi , Li Ding , Lee Spector , Scott Niekum

Foundation models are first pre-trained on vast unsupervised datasets and then fine-tuned on labeled data. Reinforcement learning, notably from human feedback (RLHF), can further align the network with the intended usage. Yet the…

Preference learning is critical for aligning large language models (LLMs) with human values, with the quality of preference datasets playing a crucial role in this process. While existing metrics primarily assess data quality based on…

Machine Learning · Computer Science 2025-03-05 Kexin Huang , Junkang Wu , Ziqian Chen , Xue Wang , Jinyang Gao , Bolin Ding , Jiancan Wu , Xiangnan He , Xiang Wang

Process reward models (PRMs) have demonstrated significant efficacy in enhancing the mathematical reasoning capabilities of large language models (LLMs) by leveraging test-time scaling (TTS). However, while most PRMs exhibit substantial…

Artificial Intelligence · Computer Science 2025-09-30 Haotian Zhang , Liu Liu , Baosheng Yu , Jiayan Qiu , Likang Xiao , Yanwei Ren , Quan Chen , Xianglong Liu

Reinforcement learning (RL) has become a standard paradigm for refining large language models (LLMs) beyond pre-training and instruction tuning. A prominent line of work is RL with verifiable rewards (RLVR), which leverages automatically…

Machine Learning · Computer Science 2025-09-23 Bonan Zhang , Zhongqi Chen , Bowen Song , Qinya Li , Fan Wu , Guihai Chen

Word alignment over parallel corpora has a wide variety of applications, including learning translation lexicons, cross-lingual transfer of language processing tools, and automatic evaluation or analysis of translation outputs. The great…

Computation and Language · Computer Science 2021-08-13 Zi-Yi Dou , Graham Neubig

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

While Reinforcement Learning from Human Feedback (RLHF) is widely used to align Large Language Models (LLMs) with human preferences, it typically assumes homogeneous preferences across users, overlooking diverse human values and minority…

Computation and Language · Computer Science 2025-10-28 Yijiang River Dong , Tiancheng Hu , Yinhong Liu , Ahmet Üstün , Nigel Collier

A promising approach for improving reasoning in large language models is to use process reward models (PRMs). PRMs provide feedback at each step of a multi-step reasoning trace, potentially improving credit assignment over outcome reward…

Large Reasoning Models (LRMs) with long chain-of-thought capabilities, optimized via reinforcement learning with verifiable rewards (RLVR), excel at objective reasoning tasks like mathematical problem solving and code generation. However,…

Computation and Language · Computer Science 2026-03-03 Yumeng Wang , Zhiyuan Fan , Jiayu Liu , Jen-tse Huang , Yi R. Fung

The prevailing approach to aligning Large Language Models (LLMs) typically relies on human or AI feedback and assumes access to specific types of preference datasets. In our work, we question the efficacy of such datasets and explore…

Machine Learning · Computer Science 2024-03-19 Hao Sun

The alignment of Large Language Models (LLMs) is critically dependent on reward models trained on costly human preference data. While recent work explores bypassing this cost with AI feedback, these methods often lack a rigorous theoretical…

Computation and Language · Computer Science 2025-07-01 Yi-Chen Li , Tian Xu , Yang Yu , Xuqin Zhang , Xiong-Hui Chen , Zhongxiang Ling , Ningjing Chao , Lei Yuan , Zhi-Hua Zhou

Recent advances in large language models (LLMs) have demonstrated significant progress in performing complex tasks. While Reinforcement Learning from Human Feedback (RLHF) has been effective in aligning LLMs with human preferences, it is…

Machine Learning · Computer Science 2025-05-30 Chaoqi Wang , Zhuokai Zhao , Yibo Jiang , Zhaorun Chen , Chen Zhu , Yuxin Chen , Jiayi Liu , Lizhu Zhang , Xiangjun Fan , Hao Ma , Sinong Wang

Learning reward functions remains the bottleneck to equip a robot with a broad repertoire of skills. Large Language Models (LLM) contain valuable task-related knowledge that can potentially aid in the learning of reward functions. However,…

Robotics · Computer Science 2024-05-17 Yuwei Zeng , Yao Mu , Lin Shao

Aligning large language models (LLMs) with human preferences has been recognized as the key to improving LLMs' interaction quality. However, in this pluralistic world, human preferences can be diversified due to annotators' different…

Artificial Intelligence · Computer Science 2024-10-08 Dun Zeng , Yong Dai , Pengyu Cheng , Longyue Wang , Tianhao Hu , Wanshun Chen , Nan Du , Zenglin Xu

Designing an effective reward function has long been a challenge in reinforcement learning, particularly for complex tasks in unstructured environments. To address this, various learning paradigms have emerged that leverage different forms…

Machine Learning · Computer Science 2025-04-29 Muhammad Qasim Elahi , Somtochukwu Oguchienti , Maheed H. Ahmed , Mahsa Ghasemi

Process Reward Models (PRMs) supervise intermediate reasoning steps in large language models (LLMs), but existing PRMs are mainly trained on general-domain data and struggle with the structured, symbolic, and fact-sensitive nature of…

Computation and Language · Computer Science 2026-05-05 Jie Zhu , Yuanchen Zhou , Shuo Jiang , Junhui Li , Lifan Guo , Feng Chen , Chi Zhang

Recent advancements in improving the reasoning capabilities of Large Language Models have underscored the efficacy of Process Reward Models (PRMs) in addressing intermediate errors through structured feedback mechanisms. This study analyzes…

Computation and Language · Computer Science 2025-06-03 Zhengyu Chen , Yudong Wang , Teng Xiao , Ruochen Zhou , Xuesheng Yang , Wei Wang , Zhifang Sui , Jingang Wang

Training multimodal process reward models (PRMs) is hard due to (i) distribution shift between training set and test set and (ii) quality imbalance across training data samples. While domain-level reweighting (e.g., DreamPRM) aligns…

Machine Learning · Computer Science 2025-10-22 Qi Cao , Pengtao Xie