paper-with-me

홈 › Papers

Inverse-Q*: Token Level Reinforcement Learning for Aligning Large Language Models Without Preference Data

2024-08-27 · Han Xia, Songyang Gao, Qiming Ge, Zhiheng Xi, Qi Zhang, Xuanjing Huang

Reinforcement Learning from Human Feedback (RLHF) has proven effective in aligning large language models with human intentions, yet it often relies on complex methodologies like Proximal Policy Optimization (PPO) that require extensive hyper-parameter tuning and present challenges in sample efficiency and stability. In this paper, we introduce Inverse-Q*, an innovative framework that transcends traditional RL methods by optimizing token-level reinforcement learning without the need for additional reward or value models. Inverse-Q* leverages direct preference optimization techniques but extends them by estimating the conditionally optimal policy directly from the model's responses, facilitating more granular and flexible policy shaping. Our approach reduces reliance on human annotation and external supervision, making it especially suitable for low-resource settings. We present extensive experimental results demonstrating that Inverse-Q* not only matches but potentially exceeds the effectiveness of PPO in terms of convergence speed and the alignment of model responses with human preferences. Our findings suggest that Inverse-Q* offers a practical and robust alternative to conventional RLHF approaches, paving the way for more efficient and adaptable model training approaches.

📄 PDF Abstract BibTeX arXiv:2408.14874

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learningReinforcement Learning

Methods 이 논문이 사용한 방법론

Entropy Regularization 설명 없음
PPO Proximal Policy Optimization, or PPO, is a policy gradient method for reinforcement learning. The motivation was to have an algorithm with the data efficiency and reliable…
SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

Supervised Fine-Tuning as Inverse Reinforcement Learning

2024-03-18 · Hao Sun

The prevailing approach to aligning Large Language Models (LLMs) typically relies on human or AI feedback and assumes access to specific types of preference datasets. In our work, we question the efficacy of such dataset…

Decision MakingImitation Learningreinforcement-learningReinforcement Learning+1

Rubrics to Tokens: Bridging Response-level Rubrics and Token-level Rewards in Instruction Following Tasks

2026-04-03 · Tianze Xu, Yanzhao Zheng, Pengrui Lu, Lyumanshan Ye 외 arxiv

Rubric-based Reinforcement Learning (RL) has emerged as a promising approach for aligning Large Language Models (LLMs) with complex, open-domain instruction following tasks. However, existing methods predominantly rely o…

Reinforcement LearningInstruction Following

SDPT: Synchronous Dual Prompt Tuning for Fusion-based Visual-Language Pre-trained Models

2024-07-16 · Yang Zhou, Yongjian Wu, Jiya Saiyin, Bingzheng Wei 외

Prompt tuning methods have achieved remarkable success in parameter-efficient fine-tuning on large pre-trained models. However, their application to dual-modal fusion-based visual-language pre-trained models (VLPMs), suc…

parameter-efficient fine-tuning

TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization

2025-06-17 · Mingkang Zhu, Xi Chen, Zhongdao Wang, Bei Yu 외

Recent advancements in reinforcement learning from human feedback have shown that utilizing fine-grained token-level reward models can substantially enhance the performance of Proximal Policy Optimization (PPO) in aligni…

Sentence-level Reward Model can Generalize Better for Aligning LLM from Human Preference

2025-03-01 · Wenjie Qiu, Yi-Chen Li, Xuqin Zhang, Tianyi Zhang 외

Learning reward models from human preference datasets and subsequently optimizing language models via reinforcement learning has emerged as a fundamental paradigm for aligning LLMs with human preferences. The performance…

Sentence