English
Related papers

Related papers: RAFT: Reward rAnked FineTuning for Generative Foun…

200 papers

Foundation models require fine-tuning to ensure their generative outputs align with intended results for specific tasks. Automating this fine-tuning process is challenging, as it typically needs human feedback that can be expensive to…

The prevailing paradigm for training large reasoning models--combining Supervised Fine-Tuning (SFT) with Reinforcement Learning with Verifiable Rewards (RLVR)--is fundamentally constrained by its reliance on high-quality, human-annotated…

Machine Learning · Computer Science 2026-03-24 Yuanfu Wang , Zhixuan Liu , Xiangtian Li , Chaochao Lu , Chao Yang

While foundation models have been exploited for various expert tasks through fine-tuning, any foundation model will become outdated due to its old knowledge or limited capability. Thus the underlying foundation model should be eventually…

Machine Learning · Computer Science 2025-02-19 Daiki Chijiwa , Taku Hasegawa , Kyosuke Nishida , Kuniko Saito , Susumu Takeuchi

Foundation models, specifically Large Language Models (LLMs), have lately gained wide-spread attention and adoption. Reinforcement Learning with Human Feedback (RLHF) involves training a reward model to capture desired behaviors, which is…

Computation and Language · Computer Science 2024-01-25 Will LeVine , Benjamin Pikus , Anthony Chen , Sean Hendryx

Reinforcement learning (RL) is a promising approach for solving robotic manipulation tasks. However, it is challenging to apply the RL algorithms directly in the real world. For one thing, RL is data-intensive and typically requires…

OpenAI's recent introduction of Reinforcement Fine-Tuning (RFT) showcases the potential of reasoning foundation model and offers a new paradigm for fine-tuning beyond simple pattern imitation. This technical report presents \emph{OpenRFT},…

Artificial Intelligence · Computer Science 2024-12-24 Yuxiang Zhang , Yuqi Yang , Jiangming Shu , Yuhang Wang , Jinlin Xiao , Jitao Sang

Learning to rank (LTR) plays a crucial role in various Information Retrieval (IR) tasks. Although supervised LTR methods based on fine-grained relevance labels (e.g., document-level annotations) have achieved significant success, their…

Information Retrieval · Computer Science 2025-08-21 Yiteng Tu , Zhichao Xu , Tao Yang , Weihang Su , Yujia Zhou , Yiqun Liu , Fen Lin , Qin Liu , Qingyao Ai

Reinforcement learning (RL) for mathematical reasoning can suffer from reward sparsity: for challenging problems, LLM fails to sample any correct trajectories, preventing RL from receiving meaningful positive feedback. At the same time,…

Machine Learning · Computer Science 2026-03-06 Yangzhen Wu , Shanda Li , Zixin Wen , Xin Zhou , Ameet Talwalkar , Yiming Yang , Wenhao Huang , Tianle Cai

Rewards serve as proxies for human preferences and play a crucial role in Reinforcement Learning from Human Feedback (RLHF). However, if these rewards are inherently imperfect, exhibiting various biases, they can adversely affect the…

Machine Learning · Computer Science 2025-11-12 Sheng Ouyang , Yulan Hu , Ge Chen , Qingyang Li , Fuzheng Zhang , Yong Liu

A promising paradigm for adapting instruction-tuned language models is to learn task-specific updates on a pretrained base model and subsequently merge them into the instruction-tuned model. However, existing approaches typically treat the…

Computation and Language · Computer Science 2026-05-05 Zhiwen Ruan , Yichao Du , Jianjie Zheng , Longyue Wang , Yun Chen , Peng Li , Jinsong Su , Yang Liu , Guanhua Chen

Aligning human preference and value is an important requirement for building contemporary foundation models and embodied AI. However, popular approaches such as reinforcement learning with human feedback (RLHF) break down the task into…

Artificial Intelligence · Computer Science 2024-12-03 Chenliang Li , Siliang Zeng , Zeyi Liao , Jiaxiang Li , Dongyeop Kang , Alfredo Garcia , Mingyi Hong

Model alignment with human preferences is an essential step in making Large Language Models (LLMs) helpful and consistent with human values. It typically consists of supervised fine-tuning (SFT) and reinforcement learning from human…

Computation and Language · Computer Science 2023-10-10 Yi Dong , Zhilin Wang , Makesh Narsimhan Sreedhar , Xianchao Wu , Oleksii Kuchaiev

Training language models via reinforcement learning often relies on imperfect proxy rewards, since ground truth rewards that precisely define the intended behavior are rarely available. Standard metrics for assessing the quality of proxy…

Machine Learning · Computer Science 2026-04-29 Shuning Shang , Hubert Strauss , Stanley Wei , Sanjeev Arora , Noam Razin

Reinforcement finetuning (RFT) has emerged as a powerful paradigm for unlocking reasoning capabilities in large language models. However, we identify a critical trade-off: while unconstrained RFT achieves strong reasoning performance, it…

Machine Learning · Computer Science 2026-02-03 Shuozhe Li , Jincheng Cao , Bodun Hu , Aryan Mokhtari , Leqi Liu , Amy Zhang

Reinforcement learning with verifiable rewards (RLVR) typically optimizes for outcome rewards without imposing constraints on intermediate reasoning. This leaves training susceptible to reward hacking, where models exploit loopholes (e.g.,…

Machine Learning · Computer Science 2026-04-20 Songtao Wang , Quang Hieu Pham , Fangcong Yin , Xinpeng Wang , Jocelyn Qiaochu Chen , Greg Durrett , Xi Ye

Reinforcement Learning frameworks, particularly those utilizing human annotations, have become an increasingly popular method for preference fine-tuning, where the outputs of a language model are tuned to match a certain set of behavioral…

Machine Learning · Computer Science 2025-10-21 Archie Chaudhury

Reward models (RMs) play a crucial role in reinforcement learning from human feedback (RLHF), aligning model behavior with human preferences. However, existing benchmarks for reward models show a weak correlation with the performance of…

Machine Learning · Computer Science 2025-05-20 Sunghwan Kim , Dongjin Kang , Taeyoon Kwon , Hyungjoo Chae , Dongha Lee , Jinyoung Yeo

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

Aligning large language models with human objectives is paramount, yet common approaches including RLHF suffer from unstable and resource-intensive training. In response to this challenge, we introduce ARGS, Alignment as Reward-Guided…

Computation and Language · Computer Science 2024-02-06 Maxim Khanov , Jirayu Burapacheep , Yixuan Li

Techniques that learn improved representations via offline data or self-supervised objectives have shown impressive results in traditional reinforcement learning (RL). Nevertheless, it is unclear how improved representation learning can…

Computation and Language · Computer Science 2024-10-25 Vaskar Nath , Dylan Slack , Jeff Da , Yuntao Ma , Hugh Zhang , Spencer Whitehead , Sean Hendryx