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

Ruobing Yao, Yifei Zhang, Shuang Song, Yuhua Liu, Neng Gao +1 more
2/12/2025
cs.CL

No confident code implementation found for this paper.

Abstract

While Retrieval-Augmented Generation (RAG) systems enhance Large Language Models (LLMs) by incorporating external knowledge, they still face persistent challenges in retrieval inefficiency and the inability of LLMs to filter out irrelevant information. We present ParetoRAG, 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 both retrieval precision and generation quality without requiring additional training or API resources. This framework has been empirically validated across various datasets, LLMs, and retrievers.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

OpenRAG: Optimizing RAG End-to-End via In-Context Retrieval Learning

85% match2025

FedRAG: A Framework for Fine-Tuning Retrieval-Augmented Generation Systems

85% match1 repo1502025

Enhancing Retrieval-Augmented Generation: A Study of Best Practices

85% match1 repo1072025

FunnelRAG: A Coarse-to-Fine Progressive Retrieval Paradigm for RAG

85% match2024

XRAG: eXamining the Core -- Benchmarking Foundational Components in Advanced Retrieval-Augmented Generation

84% match1 repo8032024

ImpRAG: Retrieval-Augmented Generation with Implicit Queries

84% match2025

Cite this paper

@article{yao2025paretorag,
  title  = {ParetoRAG: Leveraging Sentence-Context Attention for Robust and Efficient Retrieval-Augmented Generation},
  author = {Ruobing Yao and Yifei Zhang and Shuang Song and Yuhua Liu and Neng Gao and Chenyang Tu},
  year   = {2025},
  eprint = {2502.08178},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2502.08178v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2502.08178.svg)](https://codeofpaper.com/paper/2502.08178)

Discussion