English
Related papers

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

200 papers

In recent years, text-to-speech (TTS) has seen impressive advancements through large-scale language models, achieving human-level speech quality. Integrating human feedback has proven effective for enhancing robustness in these systems.…

Audio and Speech Processing · Electrical Eng. & Systems 2025-09-03 Kangxiang Xia , Xinfa Zhu , Jixun Yao , Lei Xie

Direct Preference Optimization (DPO) has emerged as a more computationally efficient alternative to Reinforcement Learning from Human Feedback (RLHF) with Proximal Policy Optimization (PPO), eliminating the need for reward models and online…

Computation and Language · Computer Science 2024-10-28 Xin Mao , Feng-Lin Li , Huimin Xu , Wei Zhang , Wang Chen , Anh Tuan Luu

Reinforcement learning from human feedback (RLHF) has evolved to be one of the main methods for fine-tuning large language models (LLMs). However, existing RLHF methods are non-robust, and their performance deteriorates if the downstream…

Machine Learning · Computer Science 2025-03-04 Debmalya Mandal , Paulius Sasnauskas , Goran Radanovic

Language model alignment is crucial for ensuring that large language models (LLMs) align with human preferences, yet it often involves sensitive user data, raising significant privacy concerns. While prior work has integrated differential…

Cryptography and Security · Computer Science 2025-05-15 Keyu Chen , Hao Tang , Qinglin Liu , Yizhao Xu

Reinforcement Learning with Human Feedback (RLHF) has become crucial for aligning Large Language Models (LLMs) with human intent. However, existing offline RLHF approaches suffer from overoptimization, where language models degrade by…

Machine Learning · Computer Science 2026-04-20 Sharan Sahu , Martin T. Wells

Learning from human preference is a paradigm used in large-scale language model (LLM) fine-tuning step to better align pretrained LLM to human preference for downstream task. In the past it uses reinforcement learning from human feedback…

Artificial Intelligence · Computer Science 2024-09-02 Shiming Xie , Hong Chen , Fred Yu , Zeye Sun , Xiuyu Wu , Yingfan Hu

Aligning Large Language Models (LLMs) to human preferences in content, style, and presentation is challenging, in part because preferences are varied, context-dependent, and sometimes inherently ambiguous. While successful, Reinforcement…

Machine Learning · Computer Science 2024-10-29 Sam Houliston , Alizée Pace , Alexander Immer , Gunnar Rätsch

Language models are aligned to emulate the collective voice of many, resulting in outputs that align with no one in particular. Steering LLMs away from generic output is possible through supervised finetuning or RLHF, but requires…

Computation and Language · Computer Science 2025-04-22 Omar Shaikh , Michelle S. Lam , Joey Hejna , Yijia Shao , Hyundong Cho , Michael S. Bernstein , Diyi Yang

Aligning large language models (LLMs) with human preferences is a critical challenge in AI research. While methods like Reinforcement Learning from Human Feedback (RLHF) and Direct Preference Optimization (DPO) are widely used, they often…

Computation and Language · Computer Science 2026-05-19 Xuan Qi , Rongwu Xu , Zhijing Jin

Enhancing the conformity of large language models (LLMs) to human preferences remains an ongoing research challenge. Recently, offline approaches such as Direct Preference Optimization (DPO) have gained prominence as attractive options due…

Machine Learning · Computer Science 2024-09-05 Kaihui Chen , Hao Yi , Qingyang Li , Tianyu Qi , Yulan Hu , Fuzheng Zhang , Yong Liu

Direct Preference Optimization (DPO) has proven effective at improving the performance of large language models (LLMs) on downstream tasks such as reasoning and alignment. In this work, we propose Step-Controlled DPO (SCDPO), a method for…

Computation and Language · Computer Science 2024-07-16 Zimu Lu , Aojun Zhou , Ke Wang , Houxing Ren , Weikang Shi , Junting Pan , Mingjie Zhan , Hongsheng Li

In this paper, we study offline Reinforcement Learning with Human Feedback (RLHF) where we aim to learn the human's underlying reward and the MDP's optimal policy from a set of trajectories induced by human choices. RLHF is challenging for…

Machine Learning · Computer Science 2023-07-04 Zihao Li , Zhuoran Yang , Mengdi Wang

Direct Preference Optimization (DPO) improves the alignment of large language models (LLMs) with human values by training directly on human preference datasets, eliminating the need for reward models. However, due to the presence of…

Artificial Intelligence · Computer Science 2024-06-11 Biqing Qi , Pengfei Li , Fangyuan Li , Junqi Gao , Kaiyan Zhang , Bowen Zhou

This paper focuses on the online saddle point problem, which involves a sequence of two-player time-varying convex-concave games. Considering the nonstationarity of the environment, we adopt the duality gap and the dynamic Nash equilibrium…

Machine Learning · Computer Science 2025-06-27 Qing-xin Meng , Jian-wei Liu

Large Language Models (LLMs) have demonstrated remarkable proficiency in English mathematical reasoning, yet a significant performance disparity persists in multilingual contexts, largely attributed to deficiencies in language…

Computation and Language · Computer Science 2026-03-27 Xu Huang , Zhejian Lai , Zixian Huang , Jiajun Chen , Shujian Huang

We study how to learn $\epsilon$-optimal strategies in zero-sum imperfect information games (IIG) with trajectory feedback. In this setting, players update their policies sequentially based on their observations over a fixed number of…

Computer Science and Game Theory · Computer Science 2023-09-06 Côme Fiegel , Pierre Ménard , Tadashi Kozuno , Rémi Munos , Vianney Perchet , Michal Valko

We introduce Adversarial Policy Optimization (AdvPO), a novel solution to the pervasive issue of reward over-optimization in Reinforcement Learning from Human Feedback (RLHF) for Large Language Models (LLMs). Over-optimization occurs when a…

Machine Learning · Computer Science 2024-07-10 Xiaoying Zhang , Jean-Francois Ton , Wei Shen , Hongning Wang , Yang Liu

The task adaptation and alignment of Large Multimodal Models (LMMs) have been significantly advanced by instruction tuning and further strengthened by recent preference optimization. Yet, most LMMs still suffer from severe modality…

Machine Learning · Computer Science 2025-10-10 Chenxi Liu , Tianyi Xiong , Yanshuo Chen , Ruibo Chen , Yihan Wu , Junfeng Guo , Tianyi Zhou , Heng Huang

At the forefront of state-of-the-art human alignment methods are preference optimization methods (*PO). Prior research has often concentrated on identifying the best-performing method, typically involving a grid search over hyperparameters,…

Computation and Language · Computer Science 2025-04-30 Kian Ahrabian , Xihui Lin , Barun Patra , Vishrav Chaudhary , Alon Benhaim , Jay Pujara , Xia Song

We propose a general framework for entropy-regularized average-reward reinforcement learning in Markov decision processes (MDPs). Our approach is based on extending the linear-programming formulation of policy optimization in MDPs to…

Machine Learning · Computer Science 2017-05-23 Gergely Neu , Anders Jonsson , Vicenç Gómez