@inproceedings{su-etal-2026-gqlbench,
title = "{GQLB}ench: A Large-Scale Cross-Domain, Cross-Dialect Benchmark for {NL}2{GQL}",
author = "Su, Yanning and
Zhou, Yuhang and
Fang, Yang and
Liu, Sen and
Ye, Guangnan and
Chai, Hongfeng",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-long.1476/",
pages = "31989--32014",
ISBN = "979-8-89176-390-6",
abstract = "Despite growing interest in NL2GQL, benchmarking progress has been constrained by the lack of resources that are simultaneously large-scale, cross-domain, and cross-dialect. To address this gap, we present **GQLBench**, a new benchmark built through an automated and scalable framework that integrates NL2SQL-to-NL2GQL conversion with graph-native data generation. GQLBench supports execution-based evaluation on both Cypher and ISO-GQL, covering hundreds of graph databases and over 20k natural language questions for each dialect. By combining converted data from mature NL2SQL resources with synthetic graph-specific queries, it captures both schema diversity from real-world relational sources and graph-native reasoning challenges, including long paths and cycles. Beyond overall performance comparison, GQLBench also enables fine-grained evaluation across dialects, graph patterns, and query complexity. Experiments on advanced LLMs show that even strong proprietary models struggle on GQLBench, with gemini-3-flash achieving only 35.40{\%} average execution accuracy across the two dialects. Our data and code are available at https://github.com/qxssadf/GQLBench."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="su-etal-2026-gqlbench">
<titleInfo>
<title>GQLBench: A Large-Scale Cross-Domain, Cross-Dialect Benchmark for NL2GQL</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yanning</namePart>
<namePart type="family">Su</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuhang</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Fang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sen</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guangnan</namePart>
<namePart type="family">Ye</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongfeng</namePart>
<namePart type="family">Chai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-390-6</identifier>
</relatedItem>
<abstract>Despite growing interest in NL2GQL, benchmarking progress has been constrained by the lack of resources that are simultaneously large-scale, cross-domain, and cross-dialect. To address this gap, we present **GQLBench**, a new benchmark built through an automated and scalable framework that integrates NL2SQL-to-NL2GQL conversion with graph-native data generation. GQLBench supports execution-based evaluation on both Cypher and ISO-GQL, covering hundreds of graph databases and over 20k natural language questions for each dialect. By combining converted data from mature NL2SQL resources with synthetic graph-specific queries, it captures both schema diversity from real-world relational sources and graph-native reasoning challenges, including long paths and cycles. Beyond overall performance comparison, GQLBench also enables fine-grained evaluation across dialects, graph patterns, and query complexity. Experiments on advanced LLMs show that even strong proprietary models struggle on GQLBench, with gemini-3-flash achieving only 35.40% average execution accuracy across the two dialects. Our data and code are available at https://github.com/qxssadf/GQLBench.</abstract>
<identifier type="citekey">su-etal-2026-gqlbench</identifier>
<location>
<url>https://aclanthology.org/2026.acl-long.1476/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>31989</start>
<end>32014</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GQLBench: A Large-Scale Cross-Domain, Cross-Dialect Benchmark for NL2GQL
%A Su, Yanning
%A Zhou, Yuhang
%A Fang, Yang
%A Liu, Sen
%A Ye, Guangnan
%A Chai, Hongfeng
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-390-6
%F su-etal-2026-gqlbench
%X Despite growing interest in NL2GQL, benchmarking progress has been constrained by the lack of resources that are simultaneously large-scale, cross-domain, and cross-dialect. To address this gap, we present **GQLBench**, a new benchmark built through an automated and scalable framework that integrates NL2SQL-to-NL2GQL conversion with graph-native data generation. GQLBench supports execution-based evaluation on both Cypher and ISO-GQL, covering hundreds of graph databases and over 20k natural language questions for each dialect. By combining converted data from mature NL2SQL resources with synthetic graph-specific queries, it captures both schema diversity from real-world relational sources and graph-native reasoning challenges, including long paths and cycles. Beyond overall performance comparison, GQLBench also enables fine-grained evaluation across dialects, graph patterns, and query complexity. Experiments on advanced LLMs show that even strong proprietary models struggle on GQLBench, with gemini-3-flash achieving only 35.40% average execution accuracy across the two dialects. Our data and code are available at https://github.com/qxssadf/GQLBench.
%U https://aclanthology.org/2026.acl-long.1476/
%P 31989-32014
Markdown (Informal)
[GQLBench: A Large-Scale Cross-Domain, Cross-Dialect Benchmark for NL2GQL](https://aclanthology.org/2026.acl-long.1476/) (Su et al., ACL 2026)
ACL
- Yanning Su, Yuhang Zhou, Yang Fang, Sen Liu, Guangnan Ye, and Hongfeng Chai. 2026. GQLBench: A Large-Scale Cross-Domain, Cross-Dialect Benchmark for NL2GQL. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 31989–32014, San Diego, California, United States. Association for Computational Linguistics.