ParetoRAG: Leveraging Sentence-Context Attention for Robust and Efficient Retrieval-Augmented Generation

Ruobing Yao, Yifei Zhang, Shuang Song, Yuhan Liu, Neng Gao, Chenyang Tu


Abstract
While Retrieval-Augmented Generation systems enhance Large Language Models by incorporating external knowledge, they still face persistent challenges in retrieval inefficiency and the inability of LLMs to filter out irrelevant information. We presentParetoRAG, an unsupervised framework that optimizes RAG systems through sentence-level refinement guided by the Pareto principle. By decomposing paragraphs into sentences and dynamically re-weighting core content while preserving contextual coherence, ParetoRAG achieves dual improvements in retrieval precision and generation quality without requiring additional training or API resources, while using only 40% of the tokens compared to traditional RAG approaches. This framework has been empirically validated across various datasets, LLMs, and retrievers. Furthermore, we show that ParetoRAG’s architectural improvements are orthogonally compatible with adaptive noise-robust models, enabling retrieval-augmented optimization and robust training to enhance generation quality mutually. This highlights complementary architectural refinements and noise mitigation, offering insights for integrating retrieval augmentation with robustness enhancement.
Anthology ID:
2025.findings-emnlp.220
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2025
Month:
November
Year:
2025
Address:
Suzhou, China
Editors:
Christos Christodoulopoulos, Tanmoy Chakraborty, Carolyn Rose, Violet Peng
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4137–4151
Language:
URL:
https://aclanthology.org/2025.findings-emnlp.220/
DOI:
Bibkey:
Cite (ACL):
Ruobing Yao, Yifei Zhang, Shuang Song, Yuhan Liu, Neng Gao, and Chenyang Tu. 2025. ParetoRAG: Leveraging Sentence-Context Attention for Robust and Efficient Retrieval-Augmented Generation. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 4137–4151, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):
ParetoRAG: Leveraging Sentence-Context Attention for Robust and Efficient Retrieval-Augmented Generation (Yao et al., Findings 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.findings-emnlp.220.pdf
Checklist:
 2025.findings-emnlp.220.checklist.pdf