English
Related papers

Related papers: Disentangling Length from Quality in Direct Prefer…

200 papers

Reinforcement Learning from Human Feedback (RLHF) has shown great potential in fine-tuning Large Language Models (LLMs) to align with human preferences. Existing methods perform preference alignment from a fixed dataset, which can be…

Machine Learning · Computer Science 2025-02-10 Chenjia Bai , Yang Zhang , Shuang Qiu , Qiaosheng Zhang , Kang Xu , Xuelong Li

Direct Preference Optimization (DPO), the efficient alternative to PPO-based RLHF, falls short on knowledge-intensive generation: standard preference signals from human annotators or LLM judges exhibit a systematic verbosity bias that…

Computation and Language · Computer Science 2026-05-13 Qiming Bao , Juho Leinonen , Paul Denny , Michael J. Witbrock

Reinforcement learning from human feedback (RLHF) has become a cornerstone of the training and alignment pipeline for large language models (LLMs). Recent advances, such as direct preference optimization (DPO), have simplified the…

Artificial Intelligence · Computer Science 2025-03-31 Syrine Belakaria , Joshua Kazdan , Charles Marx , Chris Cundy , Willie Neiswanger , Sanmi Koyejo , Barbara E. Engelhardt , Stefano Ermon

Large Reasoning Models (LRMs) have shown exceptional reasoning capabilities, but they also suffer from the issue of overthinking, often generating excessively long and redundant answers. For problems that exceed the model's capabilities,…

Machine Learning · Computer Science 2026-03-23 Yinan Xia , Haotian Zhang , Huiming Wang

Reinforcement Learning from Human Feedback (RLHF) is a powerful paradigm for aligning foundation models to human values and preferences. However, current RLHF techniques cannot account for the naturally occurring differences in individual…

Machine Learning · Computer Science 2024-08-20 Sriyash Poddar , Yanming Wan , Hamish Ivison , Abhishek Gupta , Natasha Jaques

Standard human preference-based alignment methods, such as Reinforcement Learning from Human Feedback (RLHF), are a cornerstone for aligning large language models (LLMs) with human values. However, these methods typically assume that…

Artificial Intelligence · Computer Science 2026-03-02 Xiaoyang Cao , Zelai Xu , Mo Guang , Kaiwen Long , Michiel A. Bakker , Yu Wang , Chao Yu

In practice, preference learning from human feedback depends on incomplete data with hidden context. Hidden context refers to data that affects the feedback received, but which is not represented in the data used to train a preference…

Machine Learning · Computer Science 2024-04-18 Anand Siththaranjan , Cassidy Laidlaw , Dylan Hadfield-Menell

Reinforcement Learning from Human Feedback (RLHF) has become a pivotal paradigm in artificial intelligence to align large models with human preferences. In this paper, we propose a novel statistical framework to simultaneously conduct the…

Machine Learning · Statistics 2026-05-01 Nan Lu , Ethan Lee , Ethan X. Fang , Junwei Lu

The diversity of contexts in which large language models (LLMs) are deployed requires the ability to modify or customize default model behaviors to incorporate nuanced requirements and preferences. A convenient interface to specify such…

Machine Learning · Computer Science 2024-02-19 Moritz Stephan , Alexander Khazatsky , Eric Mitchell , Annie S Chen , Sheryl Hsu , Archit Sharma , Chelsea Finn

Fine-tuning pre-trained Large Language Models (LLMs) is essential to align them with human values and intentions. This process often utilizes methods like pairwise comparisons and KL divergence against a reference LLM, focusing on the…

Computation and Language · Computer Science 2024-09-02 Yongcheng Zeng , Guoqing Liu , Weiyu Ma , Ning Yang , Haifeng Zhang , Jun Wang

The alignment of language models with human preferences is vital for their application in real-world tasks. The problem is formulated as optimizing the model's policy to maximize the expected reward that reflects human preferences with…

Computation and Language · Computer Science 2024-06-06 Haozhe Ji , Cheng Lu , Yilin Niu , Pei Ke , Hongning Wang , Jun Zhu , Jie Tang , Minlie Huang

Direct Preference Optimization (DPO) has emerged as a promising approach for aligning large language models with human preferences. While prior work mainly extends DPO from the aspect of the objective function, we instead improve DPO from…

Machine Learning · Computer Science 2026-02-17 Xun Deng , Han Zhong , Rui Ai , Fuli Feng , Zheng Wang , Xiangnan He

Direct Preference Optimization (DPO) using an implicit reward model has proven to be an effective alternative to reinforcement learning from human feedback (RLHF) for fine-tuning preference aligned large language models (LLMs). However, the…

Computation and Language · Computer Science 2024-09-30 Guoxin Chen , Minpeng Liao , Chengxi Li , Kai Fan

Online and offline RLHF methods, such as PPO and DPO, have been highly successful in aligning AI with human preferences. Despite their success, however, these methods suffer from fundamental limitations: (a) Models trained with RLHF can…

Machine Learning · Computer Science 2025-04-15 Eugene Choi , Arash Ahmadian , Matthieu Geist , Oilvier Pietquin , Mohammad Gheshlaghi Azar

Reinforcement Learning algorithms that learn from human feedback (RLHF) need to be efficient in terms of statistical complexity, computational complexity, and query complexity. In this work, we consider the RLHF setting where the feedback…

Machine Learning · Computer Science 2024-03-14 Runzhe Wu , Wen Sun

Aligning language models (LMs) with curated human feedback is critical to control their behaviors in real-world applications. Several recent policy optimization methods, such as DPO and SLiC, serve as promising alternatives to the…

Computation and Language · Computer Science 2025-01-28 Tianqi Liu , Zhen Qin , Junru Wu , Jiaming Shen , Misha Khalman , Rishabh Joshi , Yao Zhao , Mohammad Saleh , Simon Baumgartner , Jialu Liu , Peter J. Liu , Xuanhui Wang

While large language models demonstrate remarkable capabilities, they often present challenges in terms of safety, alignment with human values, and stability during training. Here, we focus on two prevalent methods used to align these…

Computation and Language · Computer Science 2023-10-26 Gabriel Mukobi , Peter Chatain , Su Fong , Robert Windesheim , Gitta Kutyniok , Kush Bhatia , Silas Alberti

Fine-tuning large language models (LLMs) on human preferences, typically through reinforcement learning from human feedback (RLHF), has proven successful in enhancing their capabilities. However, ensuring the safety of LLMs during…

Artificial Intelligence · Computer Science 2025-04-09 Wenxuan Zhang , Philip H. S. Torr , Mohamed Elhoseiny , Adel Bibi

Offline Reinforcement Learning from Human Feedback (RLHF) pipelines such as Direct Preference Optimization (DPO) train on a pre-collected preference dataset, which makes them vulnerable to preference poisoning attack. We study label flip…

Machine Learning · Computer Science 2026-05-26 Chenye Yang , Weiyu Xu , Lifeng Lai

Aligning Large Language Models (LLMs) with human feedback is crucial for their development. Existing preference optimization methods such as DPO and KTO, while improved based on Reinforcement Learning from Human Feedback (RLHF), are…

Computation and Language · Computer Science 2024-12-23 Shuo Xie , Fangzhi Zhu , Jiahui Wang , Lulu Wen , Wei Dai , Xiaowei Chen , Junxiong Zhu , Kai Zhou , Bo Zheng