English
Related papers

Related papers: Beyond Correctness: Evaluating Subjective Writing …

200 papers

In practice, rigorous reasoning is often a key driver of correct code, while Reinforcement Learning (RL) for code generation often neglects optimizing reasoning quality. Bringing process-level supervision into RL is appealing, but it faces…

Software Engineering · Computer Science 2026-05-06 Lishui Fan , Yu Zhang , Mouxiang Chen , Zhongxin Liu

Reinforcement learning from human feedback (RLHF) has been an effective technique for aligning AI systems with human values, with remarkable successes in fine-tuning large-language models recently. Most existing RLHF paradigms make the…

Artificial Intelligence · Computer Science 2024-05-28 Chanwoo Park , Mingyang Liu , Dingwen Kong , Kaiqing Zhang , Asuman Ozdaglar

Traditionally, reward models used for reinforcement learning from human feedback (RLHF) are trained to directly predict preference scores without leveraging the generation capabilities of the underlying large language model (LLM). This…

Machine Learning · Computer Science 2024-08-22 Zachary Ankner , Mansheej Paul , Brandon Cui , Jonathan D. Chang , Prithviraj Ammanabrolu

We study estimation and statistical inference for reward models used in aligning large language models (LLMs). A key component of LLM alignment is reinforcement learning from human feedback (RLHF), where humans compare pairs of…

Machine Learning · Statistics 2025-12-04 Pangpang Liu , Junwei Lu , Will Wei Sun

Reward modeling has emerged as a crucial component in aligning large language models with human values. Significant attention has focused on using reward models as a means for fine-tuning generative models. However, the reward models…

Computation and Language · Computer Science 2026-02-04 Brian Christian , Hannah Rose Kirk , Jessica A. F. Thompson , Christopher Summerfield , Tsvetomira Dumbalska

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

Reinforcement learning based fine-tuning of large language models (LLMs) on human preferences has been shown to enhance both their capabilities and safety behavior. However, in cases related to safety, without precise instructions to human…

Artificial Intelligence · Computer Science 2024-11-05 Tong Mu , Alec Helyar , Johannes Heidecke , Joshua Achiam , Andrea Vallone , Ian Kivlichan , Molly Lin , Alex Beutel , John Schulman , Lilian Weng

Large Language Models (LLMs) are increasingly applied to automate software engineering tasks, including the generation of UML class diagrams from natural language descriptions. While prior work demonstrates that LLMs can produce…

Software Engineering · Computer Science 2026-04-07 Rabia Iftikhar , Andreas Rausch

Reinforcement learning (RL) requires access to a reward function that incentivizes the right behavior, but these are notoriously hard to specify for complex tasks. Preference-based RL provides an alternative: learning policies using a…

Machine Learning · Computer Science 2021-11-05 Kimin Lee , Laura Smith , Anca Dragan , Pieter Abbeel

Reinforcement learning from human feedback (RLHF) replaces hard-to-specify rewards with pairwise trajectory preferences, yet regret-oriented theory often assumes that preference labels are generated consistently from a single ground-truth…

Machine Learning · Computer Science 2026-04-03 Ming Shi , Yingbin Liang , Ness B. Shroff , Ananthram Swami

Rewards serve as proxies for human preferences and play a crucial role in Reinforcement Learning from Human Feedback (RLHF). However, if these rewards are inherently imperfect, exhibiting various biases, they can adversely affect the…

Machine Learning · Computer Science 2025-11-12 Sheng Ouyang , Yulan Hu , Ge Chen , Qingyang Li , Fuzheng Zhang , Yong Liu

Reinforcement Learning from Human Feedback (RLHF) has emerged as a important paradigm for aligning large language models (LLMs) with human preferences during post-training. This framework typically involves two stages: first, training a…

Machine Learning · Computer Science 2025-04-08 Wenyuan Xu , Xiaochen Zuo , Chao Xin , Yu Yue , Lin Yan , Yonghui Wu

Large Language Models (LLMs) are being applied to increasingly difficult problems and use cases. To navigate their vast solution spaces effectively, LLMs need to be creative. Yet the subjective nature of creativity and the limits of human…

Reward modeling lies at the core of reinforcement learning from human feedback (RLHF), yet most existing reward models rely on scalar or pairwise judgments that fail to capture the multifaceted nature of human preferences. Recent studies…

Computation and Language · Computer Science 2026-02-04 Tianci Liu , Ran Xu , Tony Yu , Ilgee Hong , Carl Yang , Tuo Zhao , Haoyu Wang

Reward modeling (a.k.a., preference modeling) is instrumental for aligning large language models with human preferences, particularly within the context of reinforcement learning from human feedback (RLHF). While conventional reward models…

Computation and Language · Computer Science 2024-02-13 Lei Li , Yekun Chai , Shuohuan Wang , Yu Sun , Hao Tian , Ningyu Zhang , Hua Wu

Reinforcement Learning frameworks, particularly those utilizing human annotations, have become an increasingly popular method for preference fine-tuning, where the outputs of a language model are tuned to match a certain set of behavioral…

Machine Learning · Computer Science 2025-10-21 Archie Chaudhury

Reinforcement Learning from Human Feedback (RLHF) is a widely adopted approach for aligning large language models with human values. However, RLHF relies on a reward model that is trained with a limited amount of human preference data,…

Machine Learning · Computer Science 2024-10-23 Shun Zhang , Zhenfang Chen , Sunli Chen , Yikang Shen , Zhiqing Sun , Chuang Gan

Generative models, such as large language models and text-to-image diffusion models, are increasingly used to create visual designs like user interfaces (UIs) and presentation slides. Finetuning and benchmarking these generative models have…

Computer Vision and Pattern Recognition · Computer Science 2025-11-26 Yi-Hao Peng , Jeffrey P. Bigham , Jason Wu

Reinforcement Learning with Verifiable Rewards (RLVR) improves final-answer accuracy on reasoning tasks, but it does not reliably improve reasoning quality. Because outcome rewards only assess final answers, they also reward spurious…

Machine Learning · Computer Science 2026-05-19 Chenlu Ye , Zhou Yu , Ziji Zhang , Hao Chen , Narayanan Sadagopan , Jing Huang , Tong Zhang , Anurag Beniwal

Process-level Reward Models (PRMs) are crucial for complex reasoning and decision-making tasks, where each intermediate step plays an important role in the reasoning process. Since language models are prone to various types of errors during…

Computation and Language · Computer Science 2025-07-01 Mingyang Song , Zhaochen Su , Xiaoye Qu , Jiawei Zhou , Yu Cheng