Direct Nash Optimization: Teaching Language Models to Self-Improve with General Preferences

4 April 2024

Ahmed Hassan Awadallah

Tengyang Xie

ArXiv PDF HTML

Papers citing "Direct Nash Optimization: Teaching Language Models to Self-Improve with General Preferences"

36 / 36 papers shown

Title
Can RLHF be More Efficient with Imperfect Reward Models? A Policy Coverage Perspective Jiawei Huang Bingcong Li Christoph Dann Niao He OffRL 82 0 0 20 May 2025
InfoPO: On Mutual Information Maximization for Large Language Model Alignment Teng Xiao Zhen Ge Sujay Sanghavi Tian Wang Julian Katz-Samuels Marc Versage Qingjun Cui Trishul M. Chilimbi 31 0 0 13 May 2025
FuseRL: Dense Preference Optimization for Heterogeneous Model Fusion Longguang Zhong Fanqi Wan Ziyi Yang Guosheng Liang Tianyuan Shi Xiaojun Quan MoMe 57 0 0 09 Apr 2025
Stackelberg Game Preference Optimization for Data-Efficient Alignment of Language Models Xu Chu Zhixin Zhang Tianyu Jia Yujie Jin 77 0 0 25 Feb 2025
NaturalReasoning: Reasoning in the Wild with 2.8M Challenging Questions Weizhe Yuan Jane Dwivedi-Yu Song Jiang Karthik Padthe Yang Li ... Ilia Kulikov Kyunghyun Cho Yuandong Tian Jason Weston Xian Li ReLM LRM 62 10 0 24 Feb 2025
Improving LLM General Preference Alignment via Optimistic Online Mirror Descent Yuheng Zhang Dian Yu Tao Ge Linfeng Song Zhichen Zeng Haitao Mi Nan Jiang Dong Yu 58 1 0 24 Feb 2025
Simplify RLHF as Reward-Weighted SFT: A Variational Method Yuhao Du Z. Li Pengyu Cheng Zhihong Chen Yuejiao Xie Xiang Wan Anningzhe Gao 38 1 0 20 Feb 2025
Faster WIND: Accelerating Iterative Best-of- $N$ Distillation for LLM Alignment Tong Yang Jincheng Mei H. Dai Zixin Wen Shicong Cen Dale Schuurmans Yuejie Chi Bo Dai 45 4 0 20 Feb 2025
Value-Incentivized Preference Optimization: A Unified Approach to Online and Offline RLHF Shicong Cen Jincheng Mei Katayoon Goshvadi Hanjun Dai Tong Yang Sherry Yang Dale Schuurmans Yuejie Chi Bo Dai OffRL 65 23 0 20 Feb 2025
Multi-Step Alignment as Markov Games: An Optimistic Online Gradient Descent Approach with Convergence Guarantees Yongtao Wu Luca Viano Yihang Chen Zhenyu Zhu Kimon Antonakopoulos Quanquan Gu V. Cevher 54 0 0 18 Feb 2025
Preference learning made easy: Everything should be understood through win rate Lily H. Zhang Rajesh Ranganath 85 0 0 14 Feb 2025
The Battling Influencers Game: Nash Equilibria Structure of a Potential Game and Implications to Value Alignment Young Wu Yancheng Zhu Jin-Yi Cai Xiaojin Zhu 96 0 0 03 Feb 2025
LiPO: Listwise Preference Optimization through Learning-to-Rank Tianqi Liu Zhen Qin Junru Wu Jiaming Shen Misha Khalman ... Mohammad Saleh Simon Baumgartner Jialu Liu Peter J. Liu Xuanhui Wang 133 48 0 28 Jan 2025
Reinforcement Learning Enhanced LLMs: A Survey Shuhe Wang Shengyu Zhang J. Zhang Runyi Hu Xiaoya Li Tianwei Zhang Jiwei Li Fei Wu G. Wang Eduard H. Hovy OffRL 134 7 0 05 Dec 2024
Sharp Analysis for KL-Regularized Contextual Bandits and RLHF Heyang Zhao Chenlu Ye Quanquan Gu Tong Zhang OffRL 57 3 0 07 Nov 2024
Magnetic Preference Optimization: Achieving Last-iterate Convergence for Language Model Alignment Mingzhi Wang Chengdong Ma Qizhi Chen Linjian Meng Yang Han Jiancong Xiao Zhaowei Zhang Jing Huo Weijie Su Yaodong Yang 32 4 0 22 Oct 2024
Simultaneous Reward Distillation and Preference Learning: Get You a Language Model Who Can Do Both Abhijnan Nath Changsoo Jung Ethan Seefried Nikhil Krishnaswamy 134 1 0 11 Oct 2024
MACPO: Weak-to-Strong Alignment via Multi-Agent Contrastive Preference Optimization Yougang Lyu Lingyong Yan Zihan Wang Dawei Yin Pengjie Ren Maarten de Rijke Z. Z. Ren 57 6 0 10 Oct 2024
Reward-Augmented Data Enhances Direct Preference Alignment of LLMs Shenao Zhang Zhihan Liu Boyi Liu Y. Zhang Yingxiang Yang Y. Liu Liyu Chen Tao Sun Z. Wang 93 3 0 10 Oct 2024
Regressing the Relative Future: Efficient Policy Optimization for Multi-turn RLHF Zhaolin Gao Wenhao Zhan Jonathan D. Chang Gokul Swamy Kianté Brantley Jason D. Lee Wen Sun OffRL 58 3 0 06 Oct 2024
MA-RLHF: Reinforcement Learning from Human Feedback with Macro Actions Yekun Chai Haoran Sun Huang Fang Shuohuan Wang Yu Sun Hua-Hong Wu 147 1 0 03 Oct 2024
The Crucial Role of Samplers in Online Direct Preference Optimization Ruizhe Shi Runlong Zhou Simon S. Du 55 8 0 29 Sep 2024
From Lists to Emojis: How Format Bias Affects Model Alignment Xuanchang Zhang Wei Xiong Lichang Chen Tianyi Zhou Heng Huang Tong Zhang ALM 33 11 0 18 Sep 2024
Iterative Nash Policy Optimization: Aligning LLMs with General Preferences via No-Regret Learning Yuheng Zhang Dian Yu Baolin Peng Linfeng Song Ye Tian Mingyue Huo Nan Jiang Haitao Mi Dong Yu 35 15 0 30 Jun 2024
SAIL: Self-Improving Efficient Online Alignment of Large Language Models Mucong Ding Souradip Chakraborty Vibhu Agrawal Zora Che Alec Koppel Mengdi Wang Amrit Singh Bedi Furong Huang 39 9 0 21 Jun 2024
Humor in AI: Massive Scale Crowd-Sourced Preferences and Benchmarks for Cartoon Captioning Jifan Zhang Lalit P. Jain Yang Guo Jiayi Chen Kuan Lok Zhou ... Scott Sievert Timothy Rogers Kevin Jamieson Robert Mankoff Robert Nowak 36 5 0 15 Jun 2024
Self-Improving Robust Preference Optimization Eugene Choi Arash Ahmadian Matthieu Geist Oilvier Pietquin M. G. Azar 31 8 0 03 Jun 2024
Enhancing Large Vision Language Models with Self-Training on Image Comprehension Yihe Deng Pan Lu Fan Yin Ziniu Hu Sheng Shen James Y. Zou Kai-Wei Chang Wei Wang SyDa VLM LRM 44 36 0 30 May 2024
Offline Regularised Reinforcement Learning for Large Language Models Alignment Pierre Harvey Richemond Yunhao Tang Daniel Guo Daniele Calandriello M. G. Azar ... Gil Shamir Rishabh Joshi Tianqi Liu Rémi Munos Bilal Piot OffRL 46 22 0 29 May 2024
Learn Your Reference Model for Real Good Alignment Alexey Gorbatovski Boris Shaposhnikov Alexey Malakhov Nikita Surnachev Yaroslav Aksenov Ian Maksimov Nikita Balagansky Daniil Gavrilov OffRL 54 26 0 15 Apr 2024
KTO: Model Alignment as Prospect Theoretic Optimization Kawin Ethayarajh Winnie Xu Niklas Muennighoff Dan Jurafsky Douwe Kiela 170 449 0 02 Feb 2024
Self-Rewarding Language Models Weizhe Yuan Richard Yuanzhe Pang Kyunghyun Cho Xian Li Sainbayar Sukhbaatar Jing Xu Jason Weston ReLM SyDa ALM LRM 237 298 0 18 Jan 2024
A Minimaximalist Approach to Reinforcement Learning from Human Feedback Gokul Swamy Christoph Dann Rahul Kidambi Zhiwei Steven Wu Alekh Agarwal OffRL 32 94 0 08 Jan 2024
Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models Avi Singh John D. Co-Reyes Rishabh Agarwal Ankesh Anand Piyush Patil ... Yamini Bansal Ethan Dyer Behnam Neyshabur Jascha Narain Sohl-Dickstein Noah Fiedel ALM LRM ReLM SyDa 157 144 0 11 Dec 2023
Self-Consistency Improves Chain of Thought Reasoning in Language Models Xuezhi Wang Jason W. Wei Dale Schuurmans Quoc Le Ed H. Chi Sharan Narang Aakanksha Chowdhery Denny Zhou ReLM BDL LRM AI4CE 314 3,248 0 21 Mar 2022
Training language models to follow instructions with human feedback Long Ouyang Jeff Wu Xu Jiang Diogo Almeida Carroll L. Wainwright ... Amanda Askell Peter Welinder Paul Christiano Jan Leike Ryan J. Lowe OSLM ALM 313 11,915 0 04 Mar 2022