English
Related papers

Related papers: Multi-Step Alignment as Markov Games: An Optimisti…

200 papers

Alignment of large language models (LLMs) has predominantly relied on pairwise preference optimization, where annotators select the better of two responses to a prompt. While simple, this approach overlooks the opportunity to learn from…

Machine Learning · Computer Science 2026-02-11 Yuxuan Tang , Yifan Feng

Multi-turn human-AI collaboration is fundamental to deploying interactive services such as adaptive tutoring, conversational recommendation, and professional consultation. However, optimizing these interactions via reinforcement learning is…

Machine Learning · Computer Science 2026-03-26 Haoyu Wang , Yuxin Chen , Liang Luo , Buyun Zhang , Ellie Dingqiao Wen , Pan Li

We address scaling up equilibrium computation in Mean Field Games (MFGs) using Online Mirror Descent (OMD). We show that continuous-time OMD provably converges to a Nash equilibrium under a natural and well-motivated set of monotonicity…

Artificial Intelligence · Computer Science 2021-03-02 Julien Perolat , Sarah Perrin , Romuald Elie , Mathieu Laurière , Georgios Piliouras , Matthieu Geist , Karl Tuyls , Olivier Pietquin

Direct alignment algorithms such as Direct Preference Optimization (DPO) fine-tune models based on preference data, using only supervised learning instead of two-stage reinforcement learning with human feedback (RLHF). We show that DPO…

Machine Learning · Computer Science 2025-10-24 Aditya Gopalan , Sayak Ray Chowdhury , Debangshu Banerjee

Most existing results about \emph{last-iterate convergence} of learning dynamics are limited to two-player zero-sum games, and only apply under rigid assumptions about what dynamics the players follow. In this paper we provide new results…

Computer Science and Game Theory · Computer Science 2022-03-24 Ioannis Anagnostides , Ioannis Panageas , Gabriele Farina , Tuomas Sandholm

Reinforcement Learning from Human Feedback (RLHF) is crucial for aligning Large Language Models (LLMs) with human values. However, RLHF has been continuously challenged by its high complexity in implementation and computation consumption,…

Machine Learning · Computer Science 2026-03-24 Yuhao Du , Zhuo Li , Pengyu Cheng , Zhihong Chen , Yuejiao Xie , Xiang Wan , Anningzhe Gao

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

Reinforcement learning from human feedback (RLHF) has emerged as the primary method for aligning large language models (LLMs) with human preferences. While it enables LLMs to achieve human-level alignment, it often incurs significant…

Computation and Language · Computer Science 2025-03-21 Shivank Garg , Ayush Singh , Shweta Singh , Paras Chopra

We revisit the problem of solving two-player zero-sum games in the decentralized setting. We propose a simple algorithmic framework that simultaneously achieves the best rates for honest regret as well as adversarial regret, and in addition…

Computer Science and Game Theory · Computer Science 2018-06-07 Ehsan Asadi Kangarshahi , Ya-Ping Hsieh , Mehmet Fatih Sahin , Volkan Cevher

Direct preference optimization (DPO) is a form of reinforcement learning from human feedback (RLHF) where the policy is learned directly from preferential feedback. Although many models of human preferences exist, the critical task of…

Machine Learning · Computer Science 2025-03-04 Branislav Kveton , Xintong Li , Julian McAuley , Ryan Rossi , Jingbo Shang , Junda Wu , Tong Yu

AI alignment in the shape of Reinforcement Learning from Human Feedback (RLHF) is increasingly treated as a crucial ingredient for high performance large language models. Proximal Policy Optimization (PPO) has been positioned by recent…

Direct Preference Optimization (DPO) has emerged as a popular alternative to Reinforcement Learning from Human Feedback (RLHF), offering theoretical equivalence with simpler implementation. We prove this equivalence is conditional rather…

Artificial Intelligence · Computer Science 2026-05-21 Zhiqin Yang , Yonggang Zhang , Wei Xue , Dong Fang , Bo Han , Yike Guo

Aligning generative models with human preference via RLHF typically suffers from overoptimization, where an imperfectly learned reward model can misguide the generative model to output undesired responses. We investigate this problem in a…

Machine Learning · Computer Science 2024-12-05 Zhihan Liu , Miao Lu , Shenao Zhang , Boyi Liu , Hongyi Guo , Yingxiang Yang , Jose Blanchet , Zhaoran Wang

Preference optimization is a critical post-training technique used to align large language models (LLMs) with human preferences, typically by fine-tuning on ranked response pairs. While methods like Direct Preference Optimization (DPO) have…

Computation and Language · Computer Science 2025-11-12 Rhitabrat Pokharel , Yufei Tao , Ameeta Agrawal

A major challenge in aligning large language models (LLMs) with human preferences is the issue of distribution shift. LLM alignment algorithms rely on static preference datasets, assuming that they accurately represent real-world user…

Machine Learning · Computer Science 2026-01-16 Zaiyan Xu , Sushil Vemuri , Kishan Panaganti , Dileep Kalathil , Rahul Jain , Deepak Ramachandran

The growing safety concerns surrounding large language models raise an urgent need to align them with diverse human preferences to simultaneously enhance their helpfulness and safety. A promising approach is to enforce safety constraints…

Artificial Intelligence · Computer Science 2024-11-25 Xinmeng Huang , Shuo Li , Edgar Dobriban , Osbert Bastani , Hamed Hassani , Dongsheng Ding

This paper considers the problem of designing optimal algorithms for reinforcement learning in two-player zero-sum games. We focus on self-play algorithms which learn the optimal policy by playing against itself without any direct…

Machine Learning · Computer Science 2020-07-15 Yu Bai , Chi Jin , Tiancheng Yu

In the classical Reinforcement Learning from Human Feedback (RLHF) framework, Proximal Policy Optimization (PPO) is employed to learn from sparse, sentence-level rewards -- a challenging scenario in traditional deep reinforcement learning.…

Machine Learning · Computer Science 2025-05-22 Han Zhong , Zikang Shan , Guhao Feng , Wei Xiong , Xinle Cheng , Li Zhao , Di He , Jiang Bian , Liwei Wang

We introduce Stackelberg Learning from Human Feedback (SLHF), a new framework for preference optimization. SLHF frames the alignment problem as a sequential-move game between two policies: a Leader, which commits to an action, and a…

Machine Learning · Computer Science 2025-12-19 Barna Pásztor , Thomas Kleine Buening , Andreas Krause

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
‹ Prev 1 4 5 6 7 8 10 Next ›