@inproceedings{yan-etal-2026-corrective,
title = "Corrective Retrieval Augmented Generation",
author = "Yan, Shi-Qi and
Gu, Jia-Chen and
Zhu, Yun and
Ling, Zhen-Hua",
editor = "Zhang, Yue and
Xu, Ruifeng and
Purwarianti, Ayu and
Rong, Tong and
Suzuki, Jun",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {IJCNLP}-{AACL} 2026",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-aacl.151/",
pages = "2991--3003",
ISBN = "979-8-89176-444-6",
abstract = "Large language models (LLMs) inevitably exhibit hallucinations since the accuracy of generated texts cannot be secured solely by the parametric knowledge they encapsulate. Although retrieval-augmented generation (RAG) is a practicable complement to LLMs, it relies heavily on the relevance of retrieved documents, raising concerns about how the model behaves if retrieval goes wrong. To this end, we propose Corrective Retrieval Augmented Generation (CRAG), an autonomous agent that dynamically corrects and refines the retrieval content. Specifically, an agent core is introduced that perceives, decides, and executes in a closed loop. It dynamically selects and orchestrates tools, including internal retrieval, web search, keyword evaluators, semantic evaluators, and LLM evaluators, to perform multi-dimensional contextual quality evaluation and knowledge supplementation, thereby constructing accurate and precise retrieval content. Furthermore, because CRAG refines and corrects retrieved context without requiring modifications to the underlying system, it naturally serves as a plug-and-play framework that can be seamlessly integrated with a wide range of RAG-based approaches. Experiments on five datasets demonstrate that CRAG outperforms previous approaches, while its autonomous decision-making capabilities improve tool-calling efficiency and retrieval context quality."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yan-etal-2026-corrective">
<titleInfo>
<title>Corrective Retrieval Augmented Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shi-Qi</namePart>
<namePart type="family">Yan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jia-Chen</namePart>
<namePart type="family">Gu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhen-Hua</namePart>
<namePart type="family">Ling</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruifeng</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayu</namePart>
<namePart type="family">Purwarianti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Rong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Suzuki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-444-6</identifier>
</relatedItem>
<abstract>Large language models (LLMs) inevitably exhibit hallucinations since the accuracy of generated texts cannot be secured solely by the parametric knowledge they encapsulate. Although retrieval-augmented generation (RAG) is a practicable complement to LLMs, it relies heavily on the relevance of retrieved documents, raising concerns about how the model behaves if retrieval goes wrong. To this end, we propose Corrective Retrieval Augmented Generation (CRAG), an autonomous agent that dynamically corrects and refines the retrieval content. Specifically, an agent core is introduced that perceives, decides, and executes in a closed loop. It dynamically selects and orchestrates tools, including internal retrieval, web search, keyword evaluators, semantic evaluators, and LLM evaluators, to perform multi-dimensional contextual quality evaluation and knowledge supplementation, thereby constructing accurate and precise retrieval content. Furthermore, because CRAG refines and corrects retrieved context without requiring modifications to the underlying system, it naturally serves as a plug-and-play framework that can be seamlessly integrated with a wide range of RAG-based approaches. Experiments on five datasets demonstrate that CRAG outperforms previous approaches, while its autonomous decision-making capabilities improve tool-calling efficiency and retrieval context quality.</abstract>
<identifier type="citekey">yan-etal-2026-corrective</identifier>
<location>
<url>https://aclanthology.org/2026.findings-aacl.151/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>2991</start>
<end>3003</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Corrective Retrieval Augmented Generation
%A Yan, Shi-Qi
%A Gu, Jia-Chen
%A Zhu, Yun
%A Ling, Zhen-Hua
%Y Zhang, Yue
%Y Xu, Ruifeng
%Y Purwarianti, Ayu
%Y Rong, Tong
%Y Suzuki, Jun
%S Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-444-6
%F yan-etal-2026-corrective
%X Large language models (LLMs) inevitably exhibit hallucinations since the accuracy of generated texts cannot be secured solely by the parametric knowledge they encapsulate. Although retrieval-augmented generation (RAG) is a practicable complement to LLMs, it relies heavily on the relevance of retrieved documents, raising concerns about how the model behaves if retrieval goes wrong. To this end, we propose Corrective Retrieval Augmented Generation (CRAG), an autonomous agent that dynamically corrects and refines the retrieval content. Specifically, an agent core is introduced that perceives, decides, and executes in a closed loop. It dynamically selects and orchestrates tools, including internal retrieval, web search, keyword evaluators, semantic evaluators, and LLM evaluators, to perform multi-dimensional contextual quality evaluation and knowledge supplementation, thereby constructing accurate and precise retrieval content. Furthermore, because CRAG refines and corrects retrieved context without requiring modifications to the underlying system, it naturally serves as a plug-and-play framework that can be seamlessly integrated with a wide range of RAG-based approaches. Experiments on five datasets demonstrate that CRAG outperforms previous approaches, while its autonomous decision-making capabilities improve tool-calling efficiency and retrieval context quality.
%U https://aclanthology.org/2026.findings-aacl.151/
%P 2991-3003
Markdown (Informal)
[Corrective Retrieval Augmented Generation](https://aclanthology.org/2026.findings-aacl.151/) (Yan et al., Findings 2026)
ACL
- Shi-Qi Yan, Jia-Chen Gu, Yun Zhu, and Zhen-Hua Ling. 2026. Corrective Retrieval Augmented Generation. In Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026, pages 2991–3003, Hengqin, China. Association for Computational Linguistics.