English
Related papers

Related papers: Transitivity Meets Cyclicity: Explicit Preference …

200 papers

As language models become increasingly capable, users expect them to provide not only accurate responses but also behaviors aligned with diverse human preferences across a variety of scenarios. To achieve this, Reinforcement learning (RL)…

Self-play methods have demonstrated remarkable success in enhancing model capabilities across various domains. In the context of Reinforcement Learning from Human Feedback (RLHF), self-play not only boosts Large Language Model (LLM)…

Computation and Language · Computer Science 2025-04-22 Mingzhi Wang , Chengdong Ma , Qizhi Chen , Linjian Meng , Yang Han , Jiancong Xiao , Zhaowei Zhang , Jing Huo , Weijie J. Su , Yaodong Yang

This paper addresses the challenge of aligning large language models (LLMs) with diverse human preferences within federated learning (FL) environments, where standard methods often fail to adequately represent diverse viewpoints. We…

Computation and Language · Computer Science 2025-12-17 Mahmoud Srewa , Tianyu Zhao , Salma Elmalaki

In this work, we provide theoretical guarantees for reward decomposition in deterministic MDPs. Reward decomposition is a special case of Hierarchical Reinforcement Learning, that allows one to learn many policies in parallel and combine…

Machine Learning · Computer Science 2018-03-14 Tom Zahavy , Avinatan Hasidim , Haim Kaplan , Yishay Mansour

The alignment of large language models (LLMs) with human preferences is commonly achieved through Reinforcement Learning from Human Feedback (RLHF). Direct Preference Optimization (DPO) simplified this paradigm by establishing a direct…

Machine Learning · Computer Science 2025-09-26 Yuandong Tan

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

Margin-based optimization is fundamental to improving generalization and robustness in classification tasks. In the context of reward model learning from preferences within Reinforcement Learning from Human Feedback (RLHF), existing methods…

Machine Learning · Computer Science 2025-12-02 Yaswanth Chittepu , Prasann Singhal , Greg Durrett , Scott Niekum

The rapid development of large language model (LLM) alignment algorithms has resulted in a complex and fragmented landscape, with limited clarity on the effectiveness of different methods and their inter-connections. This paper introduces…

Standard human preference-based alignment methods, such as Reinforcement Learning from Human Feedback (RLHF), are a cornerstone for aligning large language models (LLMs) with human values. However, these methods typically assume that…

Artificial Intelligence · Computer Science 2026-03-02 Xiaoyang Cao , Zelai Xu , Mo Guang , Kaiwen Long , Michiel A. Bakker , Yu Wang , Chao Yu

While fusing heterogeneous open-source LLMs with varying architectures and sizes can potentially integrate the strengths of different models, existing fusion methods face significant challenges, such as vocabulary alignment and merging…

Computation and Language · Computer Science 2025-02-27 Ziyi Yang , Fanqi Wan , Longguang Zhong , Tianyuan Shi , Xiaojun Quan

The exploration-exploitation (EE) trade-off is a central challenge in reinforcement learning (RL) for large language models (LLMs). With Group Relative Policy Optimization (GRPO), training tends to be exploitation driven: entropy decreases…

Machine Learning · Computer Science 2026-01-21 Zhaochun Li , Chen Wang , Jionghao Bai , Shisheng Cui , Ge Lan , Zhou Zhao , Yue Wang

Reinforcement learning from human feedback (RLHF) has emerged as the main paradigm for aligning large language models (LLMs) with human preferences. Typically, RLHF involves the initial step of learning a reward model from human feedback,…

Aligning large language models (LLMs) with human preferences remains a key challenge in AI. Preference-based optimization methods, such as Reinforcement Learning with Human Feedback (RLHF) and Direct Preference Optimization (DPO), rely on…

Computation and Language · Computer Science 2025-05-26 Xuan Qi , Jiahao Qiu , Xinzhe Juan , Yue Wu , Mengdi Wang

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

Preference learning is a key technology for aligning language models with human values. Reinforcement Learning from Human Feedback (RLHF) is a model-based algorithm to optimize preference learning, which first fits a reward model for…

Machine Learning · Computer Science 2024-03-26 Zaifan Jiang , Xing Huang , Chao Wei

Reinforcement learning from human feedback (RLHF) is a widely used method for aligning large language models with human preferences. However, RLHF often suffers from reward model overoptimisation, in which models overfit to the reward…

Machine Learning · Computer Science 2025-09-30 Lorenz Wolf , Robert Kirk , Mirco Musolesi

Reinforcement Learning from Human Feedback aligns the outputs of Large Language Models with human values and preferences. Central to this process is the reward model (RM), which translates human feedback into training signals for optimising…

Artificial Intelligence · Computer Science 2025-09-23 Zeyu Huang , Zihan Qiu , Zili Wang , Edoardo M. Ponti , Ivan Titov

This paper studies reinforcement learning from human feedback (RLHF) for aligning large language models with human preferences. While RLHF has demonstrated promising results, many algorithms are highly sensitive to misspecifications in the…

Machine Learning · Computer Science 2025-10-30 Erhan Xu , Kai Ye , Hongyi Zhou , Luhan Zhu , Francesco Quinzan , Chengchun Shi

Direct Preference Optimization (DPO) is an effective framework for aligning large language models with human preferences, but it struggles with complex reasoning tasks. DPO optimizes for the likelihood of generating preferred over…

Artificial Intelligence · Computer Science 2026-04-23 Darsh Kachroo , Adriana Caraeni , Arjun Prasaath Anbazhagan , Brennan Lagasse , Kevin Zhu

Reinforcement Learning from Human Feedback (RLHF) is crucial for aligning large language models with human preferences. While recent research has focused on algorithmic improvements, the importance of prompt-data construction has been…

Machine Learning · Computer Science 2025-04-03 Wei Shen , Guanlin Liu , Zheng Wu , Ruofei Zhu , Qingping Yang , Chao Xin , Yu Yue , Lin Yan
‹ Prev 1 4 5 6 7 8 10 Next ›