TensorX
返回文献探索

Paper · arXiv 2410.21252

LongReward: Improving Long-context Large Language Models with AI Feedback

Jiajie Zhang, Zhongni Hou, Xin Lv, Shulin Cao, Zhenyu Hou, Yilin Niu, Lei Hou, Yuxiao Dong, Ling Feng, Juanzi Li

19 upvotesOctober 28, 2024arXiv 预印本
AI 摘要

A novel reward-based method called LongReward enhances long-context performance of supervised fine-tuned models by leveraging human-valued criteria and an off-the-shelf LLM, and it can be combined with offline RL algorithms like DPO effectively.

long-context large language modelssupervised fine-tuningreinforcement learningreward signalsLongRewardassessment pipelineoffline RL algorithm DPOlogicalityfaithfulnesscompletenesshuman-valued dimensions

Abstract

Though significant advancements have been achieved in developing long-context large language models (LLMs), the compromised quality of LLM-synthesized data for supervised fine-tuning (SFT) often affects the long-context performance of SFT models and leads to inherent limitations. In principle, reinforcement learning (RL) with appropriate reward signals can further enhance models' capacities. However, how to obtain reliable rewards in long-context scenarios remains unexplored. To this end, we propose LongReward, a novel method that utilizes an off-the-shelf LLM to provide rewards for long-context model responses from four human-valued dimensions: helpfulness, logicality, faithfulness, and completeness, each with a carefully designed assessment pipeline. By combining LongReward and offline RL algorithm DPO, we are able to effectively improve long-context SFT models. Our experiments indicate that LongReward not only significantly improves models' long-context performance but also enhances their ability to follow short instructions. We also find that long-context DPO with LongReward and conventional short-context DPO can be used together without hurting either one's performance.

北京市昌平区探索星信息技术及软件开发工作室

京ICP备2026059466号
LongReward: Improving Long-context Large Language Models with AI Feedback | TensorX