Learning to Extract Rational Evidence via Reinforcement Learning for Retrieval-Augmented Generation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917421289308160 |
|---|---|
| author | Zhao, Xinping Huang, Shouzheng Zhong, Yan Hu, Xinshuo Zhang, Meishan Hu, Baotian Zhang, Min |
| author_facet | Zhao, Xinping Huang, Shouzheng Zhong, Yan Hu, Xinshuo Zhang, Meishan Hu, Baotian Zhang, Min |
| contents | Retrieval-Augmented Generation (RAG) effectively improves the accuracy of Large Language Models (LLMs). However, retrieval noises significantly undermine the quality of LLMs' generation, necessitating the development of denoising mechanisms. Previous works extract evidence straightforwardly without deep thinking, which may risk filtering out key clues and struggle with generalization. To this end, we propose EviOmni, which learns to extract rational evidence via reasoning first and then extracting. Specifically, EviOmni integrates evidence reasoning and evidence extraction into one unified trajectory, followed by knowledge token masking to avoid information leakage, optimized via on-policy reinforcement learning with verifiable rewards in terms of answer, length, and format. Extensive experiments on five benchmark datasets show the superiority of EviOmni, which provides compact and high-quality evidence, enhances the accuracy of downstream tasks, and supports both traditional and agentic RAG systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_15586 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Learning to Extract Rational Evidence via Reinforcement Learning for Retrieval-Augmented Generation Zhao, Xinping Huang, Shouzheng Zhong, Yan Hu, Xinshuo Zhang, Meishan Hu, Baotian Zhang, Min Computation and Language Retrieval-Augmented Generation (RAG) effectively improves the accuracy of Large Language Models (LLMs). However, retrieval noises significantly undermine the quality of LLMs' generation, necessitating the development of denoising mechanisms. Previous works extract evidence straightforwardly without deep thinking, which may risk filtering out key clues and struggle with generalization. To this end, we propose EviOmni, which learns to extract rational evidence via reasoning first and then extracting. Specifically, EviOmni integrates evidence reasoning and evidence extraction into one unified trajectory, followed by knowledge token masking to avoid information leakage, optimized via on-policy reinforcement learning with verifiable rewards in terms of answer, length, and format. Extensive experiments on five benchmark datasets show the superiority of EviOmni, which provides compact and high-quality evidence, enhances the accuracy of downstream tasks, and supports both traditional and agentic RAG systems. |
| title | Learning to Extract Rational Evidence via Reinforcement Learning for Retrieval-Augmented Generation |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2507.15586 |