@inproceedings{zhang-etal-2025-autoevolve,
title = "{A}uto{E}volve: Automatically Evolving Queries for Applicable and Scalable Retrieval-Augmented Generation Benchmarking",
author = "Zhang, Ding-Chu and
Zhang, Xiaowen and
Fei, Yue and
Hu, Renjun and
Yang, Xiao-Wen and
Zhou, Zhi and
Li, Baixuan and
Li, Yu-Feng and
Shi, Xing and
Lin, Wei",
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.403/",
pages = "7624--7639",
ISBN = "979-8-89176-335-7",
abstract = "Retrieval-augmented generation (RAG) enables large language models (LLMs) to address queries beyond their internal knowledge by integrating domain knowledge in specialized corpus, which necessitates the generation of benchmarks on specific corpus to evaluate RAG systems. However, existing automated generation methods exhibit Weak Applicability and Weak Scalability. Weak Applicability refers to the reliance on metadata from specific corpora for query generation, constraining applicability to other corpora. Weak Scalability is characterized by fixed query content after generation, unable to dynamically increase difficulty, limiting scalability of the query. To overcome these issues, we propose AutoEvolve, an applicable approach for dynamically evolving queries to construct scalable RAG benchmarks. Our approach is grounded in three key innovations: (i) a corpus-agnostic method for constructing the universal entity-document graph; (ii) a suite of evolution operations designed to dynamically update queries; and (iii) a difficulty-guided metric that directs query evolution process. Through experiments on three generated benchmarks, we demonstrate that AutoEvolve evolves queries that are significantly more challenging, paving the way for more applicable and scalable RAG evaluations."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2025-autoevolve">
<titleInfo>
<title>AutoEvolve: Automatically Evolving Queries for Applicable and Scalable Retrieval-Augmented Generation Benchmarking</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ding-Chu</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaowen</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Fei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Renjun</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiao-Wen</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhi</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Baixuan</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu-Feng</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xing</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Lin</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>Retrieval-augmented generation (RAG) enables large language models (LLMs) to address queries beyond their internal knowledge by integrating domain knowledge in specialized corpus, which necessitates the generation of benchmarks on specific corpus to evaluate RAG systems. However, existing automated generation methods exhibit Weak Applicability and Weak Scalability. Weak Applicability refers to the reliance on metadata from specific corpora for query generation, constraining applicability to other corpora. Weak Scalability is characterized by fixed query content after generation, unable to dynamically increase difficulty, limiting scalability of the query. To overcome these issues, we propose AutoEvolve, an applicable approach for dynamically evolving queries to construct scalable RAG benchmarks. Our approach is grounded in three key innovations: (i) a corpus-agnostic method for constructing the universal entity-document graph; (ii) a suite of evolution operations designed to dynamically update queries; and (iii) a difficulty-guided metric that directs query evolution process. Through experiments on three generated benchmarks, we demonstrate that AutoEvolve evolves queries that are significantly more challenging, paving the way for more applicable and scalable RAG evaluations.</abstract>
<identifier type="citekey">zhang-etal-2025-autoevolve</identifier>
<location>
<url>https://aclanthology.org/2025.findings-emnlp.403/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>7624</start>
<end>7639</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AutoEvolve: Automatically Evolving Queries for Applicable and Scalable Retrieval-Augmented Generation Benchmarking
%A Zhang, Ding-Chu
%A Zhang, Xiaowen
%A Fei, Yue
%A Hu, Renjun
%A Yang, Xiao-Wen
%A Zhou, Zhi
%A Li, Baixuan
%A Li, Yu-Feng
%A Shi, Xing
%A Lin, Wei
%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 zhang-etal-2025-autoevolve
%X Retrieval-augmented generation (RAG) enables large language models (LLMs) to address queries beyond their internal knowledge by integrating domain knowledge in specialized corpus, which necessitates the generation of benchmarks on specific corpus to evaluate RAG systems. However, existing automated generation methods exhibit Weak Applicability and Weak Scalability. Weak Applicability refers to the reliance on metadata from specific corpora for query generation, constraining applicability to other corpora. Weak Scalability is characterized by fixed query content after generation, unable to dynamically increase difficulty, limiting scalability of the query. To overcome these issues, we propose AutoEvolve, an applicable approach for dynamically evolving queries to construct scalable RAG benchmarks. Our approach is grounded in three key innovations: (i) a corpus-agnostic method for constructing the universal entity-document graph; (ii) a suite of evolution operations designed to dynamically update queries; and (iii) a difficulty-guided metric that directs query evolution process. Through experiments on three generated benchmarks, we demonstrate that AutoEvolve evolves queries that are significantly more challenging, paving the way for more applicable and scalable RAG evaluations.
%U https://aclanthology.org/2025.findings-emnlp.403/
%P 7624-7639
Markdown (Informal)
[AutoEvolve: Automatically Evolving Queries for Applicable and Scalable Retrieval-Augmented Generation Benchmarking](https://aclanthology.org/2025.findings-emnlp.403/) (Zhang et al., Findings 2025)
ACL
- Ding-Chu Zhang, Xiaowen Zhang, Yue Fei, Renjun Hu, Xiao-Wen Yang, Zhi Zhou, Baixuan Li, Yu-Feng Li, Xing Shi, and Wei Lin. 2025. AutoEvolve: Automatically Evolving Queries for Applicable and Scalable Retrieval-Augmented Generation Benchmarking. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 7624–7639, Suzhou, China. Association for Computational Linguistics.