English
Related papers

Related papers: Distributional Preference Learning: Understanding …

200 papers

We present a fine-grained theoretical analysis of the performance gap between two-stage reinforcement learning from human feedback~(RLHF) and direct preference optimization~(DPO). Our study decomposes this gap into two sources: the explicit…

Machine Learning · Computer Science 2026-05-13 Ruizhe Shi , Minhak Song , Runlong Zhou , Zihan Zhang , Maryam Fazel , Simon S. Du

The complexity of designing reward functions has been a major obstacle to the wide application of deep reinforcement learning (RL) techniques. Describing an agent's desired behaviors and properties can be difficult, even for experts. A new…

Machine Learning · Computer Science 2024-05-09 Wanqi Xue , Bo An , Shuicheng Yan , Zhongwen Xu

Aligning large language models (LLM) with human preference plays a key role in building modern generative models and can be achieved by reinforcement learning from human feedback (RLHF). Despite their superior performance, current RLHF…

Machine Learning · Computer Science 2025-02-12 Kaixuan Ji , Jiafan He , Quanquan Gu

Preference alignment in Large Language Models (LLMs) has significantly improved their ability to adhere to human instructions and intentions. However, existing direct alignment algorithms primarily focus on relative preferences and often…

Machine Learning · Computer Science 2025-05-13 Shenao Zhang , Zhihan Liu , Boyi Liu , Yufeng Zhang , Yingxiang Yang , Yongfei Liu , Liyu Chen , Tao Sun , Zhaoran Wang

Preference-based reinforcement learning (RL) is a key paradigm for aligning policies with human judgments, yet its theoretical behavior in distributed settings where preference data are fragmented across heterogeneous users remains poorly…

Machine Learning · Computer Science 2026-05-21 Zhanhong Jiang

Aligning large language models (LLMs) with human preferences has become essential for safe and beneficial AI deployment. While Reinforcement Learning from Human Feedback (RLHF) established the dominant paradigm, a proliferation of…

Artificial Intelligence · Computer Science 2026-01-13 Tarun Raheja , Nilay Pochhi

Large Language Models (LLMs) aligned using Reinforcement Learning from Human Feedback (RLHF) have shown remarkable generation abilities in numerous tasks. However, collecting high-quality human preferences creates costly bottlenecks in…

Machine Learning · Computer Science 2025-06-10 Nirjhar Das , Souradip Chakraborty , Aldo Pacchiano , Sayak Ray Chowdhury

Learning human preferences in language models remains fundamentally challenging, as reward modeling relies on subtle, subjective comparisons or shades of gray rather than clear-cut labels. This study investigates the limits of current…

Computation and Language · Computer Science 2026-04-03 Simona-Vasilica Oprea , Adela Bâra

Reinforcement Learning from Human Feedback (RLHF) is widely used to align Language Models (LMs) with human preferences. However, existing approaches often neglect individual user preferences, leading to suboptimal personalization. We…

Machine Learning · Computer Science 2024-10-21 Allison Lau , Younwoo Choi , Vahid Balazadeh , Keertana Chidambaram , Vasilis Syrgkanis , Rahul G. Krishnan

Large language models (LLMs) have achieved remarkable success, yet aligning their generations with human preferences remains a critical challenge. Existing approaches to preference modeling often rely on an explicit or implicit reward…

Computation and Language · Computer Science 2025-05-09 Zhuocheng Gong , Jian Guan , Wei Wu , Huishuai Zhang , Dongyan Zhao

Recent progress in strengthening the capabilities of large language models has stemmed from applying reinforcement learning to domains with automatically verifiable outcomes. A key question is whether we can similarly use RL to optimize for…

Machine Learning · Computer Science 2025-05-27 Eric Zhao , Jessica Dai , Pranjal Awasthi

Re-inforcement learning from human feedback (RLHF) has been effective in the task of AI alignment. However, one of the key assumptions of RLHF is that the annotators (referred to as workers from here on out) have a homogeneous response…

Human-Computer Interaction · Computer Science 2026-01-29 Sarvesh Shashidhar , Abhishek Mishra , Madhav Kotecha

Reinforcement learning from human feedback (RLHF) provides a principled framework for aligning AI systems with human preference data. For various reasons, e.g., personal bias, context ambiguity, lack of training, etc, human annotators may…

Machine Learning · Computer Science 2024-07-10 Alexander Bukharin , Ilgee Hong , Haoming Jiang , Zichong Li , Qingru Zhang , Zixuan Zhang , Tuo Zhao

The prevalent deployment of learning from human preferences through reinforcement learning (RLHF) relies on two important approximations: the first assumes that pairwise preferences can be substituted with pointwise rewards. The second…

Artificial Intelligence · Computer Science 2023-11-23 Mohammad Gheshlaghi Azar , Mark Rowland , Bilal Piot , Daniel Guo , Daniele Calandriello , Michal Valko , Rémi Munos

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

Deep Reinforcement Learning is widely used for aligning Large Language Models (LLM) with human preference. However, the conventional reward modelling is predominantly dependent on human annotations provided by a select cohort of…

Artificial Intelligence · Computer Science 2024-05-31 Dexun Li , Cong Zhang , Kuicai Dong , Derrick Goh Xin Deik , Ruiming Tang , Yong Liu

With the rapid development of Large Language Models (LLMs), numerous Reinforcement Learning from Human Feedback (RLHF) algorithms have been introduced to improve model safety and alignment with human preferences. These algorithms can be…

Machine Learning · Computer Science 2025-02-06 Xuerui Su , Yue Wang , Jinhua Zhu , Mingyang Yi , Feng Xu , Zhiming Ma , Yuting Liu

Human feedback can alter language models in unpredictable and undesirable ways, as practitioners lack a clear understanding of what feedback data encodes. While prior work studies preferences over certain attributes (e.g., length or…

Computation and Language · Computer Science 2026-04-14 Rajiv Movva , Smitha Milli , Sewon Min , Emma Pierson

Reinforcement learning from human feedback (RLHF) has been an effective technique for aligning AI systems with human values, with remarkable successes in fine-tuning large-language models recently. Most existing RLHF paradigms make the…

Artificial Intelligence · Computer Science 2024-05-28 Chanwoo Park , Mingyang Liu , Dingwen Kong , Kaiqing Zhang , Asuman Ozdaglar

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