@inproceedings{canby-etal-2025-benchmarking,
title = "Benchmarking Query-Conditioned Natural Language Inference",
author = "Canby, Marc E. and
Chen, Xinchi and
Niu, Xing and
Chen, Jifan and
Min, Bonan and
Aydore, Sergul and
Castelli, Vittorio",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-acl.765/",
doi = "10.18653/v1/2025.findings-acl.765",
pages = "14808--14835",
ISBN = "979-8-89176-256-5",
abstract = "The growing excitement around the ability of large language models (LLMs) to tackle various tasks has been tempered by their propensity for generating unsubstantiated information (hallucination) and by their inability to effectively handle inconsistent inputs. To detect such issues, we propose the novel task of Query-Conditioned Natural Language Inference (QC-NLI), where the goal is to determine the semantic relationship (e.g. entailment or not entailment) between two documents conditioned on a query; we demonstrate that many common tasks regarding inconsistency detection can be formulated as QC-NLI problems. We focus on three applications in particular: fact verification, intrinsic hallucination detection, and document inconsistency detection. We convert existing datasets for these tasks into the QC-NLI format, and manual annotation confirms their high quality. Finally, we employ zero- and few-shot prompting methods to solve the QC-NLI prediction problem for each task, showing the critical importance of conditioning on the query."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="canby-etal-2025-benchmarking">
<titleInfo>
<title>Benchmarking Query-Conditioned Natural Language Inference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marc</namePart>
<namePart type="given">E</namePart>
<namePart type="family">Canby</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinchi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xing</namePart>
<namePart type="family">Niu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jifan</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bonan</namePart>
<namePart type="family">Min</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sergul</namePart>
<namePart type="family">Aydore</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vittorio</namePart>
<namePart type="family">Castelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-256-5</identifier>
</relatedItem>
<abstract>The growing excitement around the ability of large language models (LLMs) to tackle various tasks has been tempered by their propensity for generating unsubstantiated information (hallucination) and by their inability to effectively handle inconsistent inputs. To detect such issues, we propose the novel task of Query-Conditioned Natural Language Inference (QC-NLI), where the goal is to determine the semantic relationship (e.g. entailment or not entailment) between two documents conditioned on a query; we demonstrate that many common tasks regarding inconsistency detection can be formulated as QC-NLI problems. We focus on three applications in particular: fact verification, intrinsic hallucination detection, and document inconsistency detection. We convert existing datasets for these tasks into the QC-NLI format, and manual annotation confirms their high quality. Finally, we employ zero- and few-shot prompting methods to solve the QC-NLI prediction problem for each task, showing the critical importance of conditioning on the query.</abstract>
<identifier type="citekey">canby-etal-2025-benchmarking</identifier>
<identifier type="doi">10.18653/v1/2025.findings-acl.765</identifier>
<location>
<url>https://aclanthology.org/2025.findings-acl.765/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>14808</start>
<end>14835</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Benchmarking Query-Conditioned Natural Language Inference
%A Canby, Marc E.
%A Chen, Xinchi
%A Niu, Xing
%A Chen, Jifan
%A Min, Bonan
%A Aydore, Sergul
%A Castelli, Vittorio
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Findings of the Association for Computational Linguistics: ACL 2025
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-256-5
%F canby-etal-2025-benchmarking
%X The growing excitement around the ability of large language models (LLMs) to tackle various tasks has been tempered by their propensity for generating unsubstantiated information (hallucination) and by their inability to effectively handle inconsistent inputs. To detect such issues, we propose the novel task of Query-Conditioned Natural Language Inference (QC-NLI), where the goal is to determine the semantic relationship (e.g. entailment or not entailment) between two documents conditioned on a query; we demonstrate that many common tasks regarding inconsistency detection can be formulated as QC-NLI problems. We focus on three applications in particular: fact verification, intrinsic hallucination detection, and document inconsistency detection. We convert existing datasets for these tasks into the QC-NLI format, and manual annotation confirms their high quality. Finally, we employ zero- and few-shot prompting methods to solve the QC-NLI prediction problem for each task, showing the critical importance of conditioning on the query.
%R 10.18653/v1/2025.findings-acl.765
%U https://aclanthology.org/2025.findings-acl.765/
%U https://doi.org/10.18653/v1/2025.findings-acl.765
%P 14808-14835
Markdown (Informal)
[Benchmarking Query-Conditioned Natural Language Inference](https://aclanthology.org/2025.findings-acl.765/) (Canby et al., Findings 2025)
ACL
- Marc E. Canby, Xinchi Chen, Xing Niu, Jifan Chen, Bonan Min, Sergul Aydore, and Vittorio Castelli. 2025. Benchmarking Query-Conditioned Natural Language Inference. In Findings of the Association for Computational Linguistics: ACL 2025, pages 14808–14835, Vienna, Austria. Association for Computational Linguistics.