English
Related papers

Related papers: OPPO: Accelerating PPO-based RLHF via Pipeline Ove…

200 papers

Reinforcement learning from human feedback (RLHF) has emerged as the standard paradigm for aligning large language models with human preferences. However, reward-based methods grounded in the Bradley-Terry assumption struggle to capture the…

Artificial Intelligence · Computer Science 2026-04-08 Fang Wu , Xu Huang , Weihao Xuan , Zhiwei Zhang , Yijia Xiao , Guancheng Wan , Xiaomin Li , Bing Hu , Peng Xia , Jure Leskovec , Yejin Choi

Recently, test-time scaling Large Language Models (LLMs) have demonstrated exceptional reasoning capabilities across scientific and professional tasks by generating long chains-of-thought (CoT). As a crucial component for developing these…

Reinforcement learning (RL) has become central to enhancing reasoning in large language models (LLMs). Yet on-policy algorithms such as Group Relative Policy Optimization (GRPO) often suffer in early training: noisy gradients from…

Machine Learning · Computer Science 2026-03-19 Ziyan Wang , Zheng Wang , Xingwei Qu , Qi Cheng , Jie Fu , Shengpu Tang , Minjia Zhang , Xiaoming Huo

Reward inference (learning a reward model from human preferences) is a critical intermediate step in the Reinforcement Learning from Human Feedback (RLHF) pipeline for fine-tuning Large Language Models (LLMs). In practice, RLHF faces…

Machine Learning · Computer Science 2025-03-04 Qining Zhang , Lei Ying

Recent advances in large video-language models (VLMs) rely on extensive fine-tuning techniques that strengthen alignment between textual and visual comprehension. Leading pipelines typically pair supervised fine-tuning (SFT) with…

Computer Vision and Pattern Recognition · Computer Science 2025-10-06 Derek Shi , Ruben Glatt , Christine Klymko , Shubham Mohole , Hongjun Choi , Shashank Kushwaha , Sam Sakla , Felipe Leno da Silva

Reward-based alignment methods for large language models (LLMs) face two key limitations: vulnerability to reward hacking, where models exploit flaws in the reward signal; and reliance on brittle, labor-intensive prompt engineering when…

Computation and Language · Computer Science 2025-05-20 Zae Myung Kim , Chanwoo Park , Vipul Raheja , Suin Kim , Dongyeop Kang

Inverse Reinforcement Learning (IRL) and Reinforcement Learning from Human Feedback (RLHF) are pivotal methodologies in reward learning, which involve inferring and shaping the underlying reward function of sequential decision-making…

Machine Learning · Computer Science 2024-10-16 Kihyun Kim , Jiawei Zhang , Asuman Ozdaglar , Pablo A. Parrilo

Reinforcement Learning from Human Feedback (RLHF) is the standard for aligning Large Language Models (LLMs), yet recent progress has moved beyond canonical text-based methods. This survey synthesizes the new frontier of alignment research…

Machine Learning · Computer Science 2025-11-07 Raghav Sharma , Manan Mehta , Sai Tiger Raina

Large language models are commonly trained through multi-stage post-training: first via RLHF, then fine-tuned for other downstream objectives. Yet even small downstream updates can compromise earlier learned behaviors (e.g., safety),…

Machine Learning · Computer Science 2026-05-13 Mahdi Sabbaghi , George Pappas , Adel Javanmard , Hamed Hassani

Reinforcement Learning from Human Feedback (RLHF), using algorithms like Proximal Policy Optimization (PPO), aligns Large Language Models (LLMs) with human values but is costly and unstable. Alternatives have been proposed to replace PPO or…

Computation and Language · Computer Science 2026-04-03 Liang Zhu , Feiteng Fang , Yuelin Bai , Longze Chen , Zhexiang Zhang , Minghuan Tan , Min Yang

Given the high computational cost of preference alignment training of large language models (LLMs), exploring efficient methods to reduce the training overhead remains an important and compelling research problem. Motivated by the…

Machine Learning · Computer Science 2025-06-02 Chujie Zheng , Ziqi Wang , Heng Ji , Minlie Huang , Nanyun Peng

Fine-tuning large language models (LLMs) on human preferences, typically through reinforcement learning from human feedback (RLHF), has proven successful in enhancing their capabilities. However, ensuring the safety of LLMs during…

Artificial Intelligence · Computer Science 2025-04-09 Wenxuan Zhang , Philip H. S. Torr , Mohamed Elhoseiny , Adel Bibi

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

A key technology for the development of large language models (LLMs) involves instruction tuning that helps align the models' responses with human expectations to realize impressive learning abilities. Two major approaches for instruction…

Computation and Language · Computer Science 2023-08-03 Viet Dac Lai , Chien Van Nguyen , Nghia Trung Ngo , Thuat Nguyen , Franck Dernoncourt , Ryan A. Rossi , Thien Huu Nguyen

This work identifies the Energy Loss Phenomenon in Reinforcement Learning from Human Feedback (RLHF) and its connection to reward hacking. Specifically, energy loss in the final layer of a Large Language Model (LLM) gradually increases…

Machine Learning · Computer Science 2025-06-03 Yuchun Miao , Sen Zhang , Liang Ding , Yuqi Zhang , Lefei Zhang , Dacheng Tao

With the rapid development and widespread application of Large Language Models (LLMs), their potential safety risks have attracted widespread attention. Reinforcement Learning from Human Feedback (RLHF) has been adopted to enhance the…

Artificial Intelligence · Computer Science 2026-03-25 Shiji Zhao , Mengyang Wang , Shukun Xiong , Fangzhou Chen , Qihui Zhu , Shouwei Ruan , Yisong Xiao , Ranjie Duan , Xun Chen , XingXing Wei

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

On-policy reinforcement learning methods, like Trust Region Policy Optimization (TRPO) and Proximal Policy Optimization (PPO), often demand extensive data per update, leading to sample inefficiency. This paper introduces Reflective Policy…

Machine Learning · Computer Science 2024-06-07 Yaozhong Gan , Renye Yan , Zhe Wu , Junliang Xing

Reinforcement Learning with Human Feedback (RLHF) has achieved great success in aligning large language models (LLMs) with human preferences. Prevalent RLHF approaches are reward-based, following the Bradley-Terry (BT) model assumption,…

Machine Learning · Computer Science 2025-03-04 Yuheng Zhang , Dian Yu , Baolin Peng , Linfeng Song , Ye Tian , Mingyue Huo , Nan Jiang , Haitao Mi , Dong Yu

Direct Preference Optimization (DPO) using an implicit reward model has proven to be an effective alternative to reinforcement learning from human feedback (RLHF) for fine-tuning preference aligned large language models (LLMs). However, the…

Computation and Language · Computer Science 2024-09-30 Guoxin Chen , Minpeng Liao , Chengxi Li , Kai Fan