English
Related papers

Related papers: Decomposing the Delta: What Do Models Actually Lea…

200 papers

Direct Preference Optimization (DPO) is an effective approach for aligning protein language models with experimental design goals. However, DPO faces a scalability bottleneck: the number of possible training pairs grows quadratically with…

Machine Learning · Computer Science 2025-11-27 Constance Ferragu , Jonathan D. Ziegler , Nicolas Deutschmann , Arthur Lindoulsi , Eli Bixby , Cradle ML Team

Preferences within a group of people are not uniform but follow a distribution. While existing alignment methods like Direct Preference Optimization (DPO) attempt to steer models to reflect human preferences, they struggle to capture the…

Computation and Language · Computer Science 2025-05-14 Binwei Yao , Zefan Cai , Yun-Shiuan Chuang , Shanglin Yang , Ming Jiang , Diyi Yang , Junjie Hu

Recent advancements in Large Language Models (LLMs) have been remarkable, with new models consistently surpassing their predecessors. These advancements are underpinned by extensive research on various training mechanisms. Among these,…

Computation and Language · Computer Science 2024-12-12 Hansle Gwon , Imjin Ahn , Young-Hak Kim , Sanghyun Park , Tae Joon Jun

Direct Preference Optimization (DPO) has gained attention as an efficient alternative to reinforcement learning from human feedback (RLHF) for aligning large language models (LLMs) with human preferences. Despite its advantages, DPO suffers…

Computation and Language · Computer Science 2025-02-21 Ruichen Shao , Bei Li , Gangao Liu , Yang Chen , Xiang Zhou , Jingang Wang , Xunliang Cai , Peng Li

How can Large Language Models (LLMs) be aligned with human intentions and values? A typical solution is to gather human preference on model outputs and finetune the LLMs accordingly while ensuring that updates do not deviate too far from a…

Computation and Language · Computer Science 2024-05-28 Hung Le , Quan Tran , Dung Nguyen , Kien Do , Saloni Mittal , Kelechi Ogueji , Svetha Venkatesh

Aligning intelligent agents with human preferences and values is important. This paper examines two popular alignment methods: Direct Preference Optimization (DPO) and Reward-Model-Based Policy Optimization (RMB-PO). A variant of RMB-PO,…

Machine Learning · Computer Science 2024-02-27 Ziniu Li , Tian Xu , Yang Yu

As large language models (LLMs) become more capable, fine-tuning techniques for aligning with human intent are increasingly important. A key consideration for aligning these models is how to most effectively use human resources, or model…

Machine Learning · Computer Science 2024-07-01 William Muldrew , Peter Hayes , Mingtian Zhang , David Barber

This study evaluates Direct Preference Optimization (DPO) and its variants for aligning Large Language Models (LLMs) with human preferences, testing three configurations: (1) with Supervised Fine Tuning (SFT), (2) without SFT, and (3)…

Computation and Language · Computer Science 2025-02-11 Amir Saeidi , Shivanshu Verma , Md Nayem Uddin , Chitta Baral

Direct Preference Optimization (DPO), a standard method for aligning language models with human preferences, is traditionally applied to offline preferences. Recent studies show that DPO benefits from iterative training with online…

Computation and Language · Computer Science 2024-06-18 Jie Liu , Zhanhui Zhou , Jiaheng Liu , Xingyuan Bu , Chao Yang , Han-Sen Zhong , Wanli Ouyang

Recent advancements in the field of large language models, particularly through the Chain of Thought (CoT) approach, have demonstrated significant improvements in solving complex problems. However, existing models either tend to sacrifice…

Computation and Language · Computer Science 2025-12-30 Yijiong Yu

As AI systems become more capable, deceptive behaviors can undermine evaluation and mislead users at deployment. Recent work has shown that lie detectors can accurately classify deceptive behavior, but they are not typically used in the…

Machine Learning · Computer Science 2025-11-19 Chris Cundy , Adam Gleave

Supervised Fine-Tuning (SFT) has been a go-to and effective method for enhancing long chain-of-thought (CoT) reasoning in relatively small LLMs by fine-tuning them with long CoT responses from larger LLMs. To continually improve reasoning…

Machine Learning · Computer Science 2025-02-20 Wang Yang , Hongye Jin , Jingfeng Yang , Vipin Chaudhary , Xiaotian Han

Aligning language models with human preferences through reinforcement learning from human feedback is crucial for their safe and effective deployment. The human preference is typically represented through comparison where one response is…

Machine Learning · Computer Science 2025-07-15 Hoang Anh Just , Ming Jin , Anit Sahu , Huy Phan , Ruoxi Jia

Reinforcement Learning from Human Feedback (RLHF) has become central to aligning large language models with human values, typically by first learning a reward model from preference data which is then used to update the model with…

Machine Learning · Computer Science 2025-10-21 Keertana Chidambaram , Karthik Vinay Seetharaman , Vasilis Syrgkanis

Direct Preference Optimization (DPO) is broadly utilized for aligning Large Language Models (LLMs) with human values because of its flexibility. Despite its effectiveness, it has been observed that the capability of DPO to generate…

Machine Learning · Computer Science 2025-05-20 Wenqiao Zhu , Ji Liu , Lulu Wang , Jun Wu , Yulun Zhang

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

Varied approaches for aligning language models have been proposed, including supervised fine-tuning, RLHF, and direct optimization methods such as DPO. Although DPO has rapidly gained popularity due to its straightforward training process…

Computation and Language · Computer Science 2024-08-08 Prasann Singhal , Nathan Lambert , Scott Niekum , Tanya Goyal , Greg Durrett

As development of large language models (LLM) progresses, aligning them with human preferences has become increasingly important. We propose stepwise DPO (sDPO), an extension of the recently popularized direct preference optimization (DPO)…

Computation and Language · Computer Science 2024-10-08 Dahyun Kim , Yungi Kim , Wonho Song , Hyeonwoo Kim , Yunsu Kim , Sanghoon Kim , Chanjun Park

Reinforcement Learning from Human Feedback (RLHF) has become central to aligning large language models with human values, typically by first learning a reward model from preference data which is then used to update the model with…

Artificial Intelligence · Computer Science 2025-10-20 Keertana Chidambaram , Karthik Vinary Seetharaman , Vasilis Syrgkanis

Preference optimization has become an important post-training paradigm for improving the reasoning abilities of large language models. Existing methods typically rely on externally constructed preference data, using preferred and…

Computation and Language · Computer Science 2026-05-13 Yifan Le