@inproceedings{yao-etal-2025-paretorag,
title = "{P}areto{RAG}: Leveraging Sentence-Context Attention for Robust and Efficient Retrieval-Augmented Generation",
author = "Yao, Ruobing and
Zhang, Yifei and
Song, Shuang and
Liu, Yuhan and
Gao, Neng and
Tu, Chenyang",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-emnlp.220/",
pages = "4137--4151",
ISBN = "979-8-89176-335-7",
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."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yao-etal-2025-paretorag">
<titleInfo>
<title>ParetoRAG: Leveraging Sentence-Context Attention for Robust and Efficient Retrieval-Augmented Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ruobing</namePart>
<namePart type="family">Yao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yifei</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuang</namePart>
<namePart type="family">Song</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuhan</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Neng</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenyang</namePart>
<namePart type="family">Tu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-335-7</identifier>
</relatedItem>
<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.</abstract>
<identifier type="citekey">yao-etal-2025-paretorag</identifier>
<location>
<url>https://aclanthology.org/2025.findings-emnlp.220/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>4137</start>
<end>4151</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ParetoRAG: Leveraging Sentence-Context Attention for Robust and Efficient Retrieval-Augmented Generation
%A Yao, Ruobing
%A Zhang, Yifei
%A Song, Shuang
%A Liu, Yuhan
%A Gao, Neng
%A Tu, Chenyang
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Findings of the Association for Computational Linguistics: EMNLP 2025
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-335-7
%F yao-etal-2025-paretorag
%X 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.
%U https://aclanthology.org/2025.findings-emnlp.220/
%P 4137-4151
Markdown (Informal)
[ParetoRAG: Leveraging Sentence-Context Attention for Robust and Efficient Retrieval-Augmented Generation](https://aclanthology.org/2025.findings-emnlp.220/) (Yao et al., Findings 2025)
ACL