@inproceedings{xu-etal-2026-gavel,
title = "{GAVEL}: Evidence-Contract Debate with Mechanized Scrutiny for Provenance-Grounded Fact-Checking",
author = "Xu, Ruoyu and
Li, Gaoxiang and
Sheng, Victor S.",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-acl.1789/",
doi = "10.18653/v1/2026.findings-acl.1789",
pages = "35907--35920",
ISBN = "979-8-89176-395-1",
abstract = "Evidence-grounded fact-checking requires predicting claim veracity while returning faithful evidence at fine granularity, including exact sentences, table cells, and complete multi-document chains. Although large language models enable decomposition, planning, and multi-agent verification, they can still produce convincing rationales with weak provenance, especially under heterogeneous evidence and multi-hop requirements. We propose GAVEL, a multi-agent debate framework that enforces evidence grounding throughout inference. GAVEL introduces an Evidence Contract that requires debaters to state atomic subclaims and bind each to explicit evidence units, and a Mechanized Chain of Scrutiny in which a neutral Scrutinizer audits outputs and performs deterministic validation of cited identifiers and quoted spans. A Judge then selects a sufficient evidence set and produces the final decision. Experiments on FEVEROUS and HOVER in an open-book setting show that GAVEL improves provenance-aware metrics that jointly require correct labels and correct, complete evidence over strong recent baselines. Ablations confirm that both evidence binding and mechanized citation validation are key to the gains."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-etal-2026-gavel">
<titleInfo>
<title>GAVEL: Evidence-Contract Debate with Mechanized Scrutiny for Provenance-Grounded Fact-Checking</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ruoyu</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gaoxiang</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Victor</namePart>
<namePart type="given">S</namePart>
<namePart type="family">Sheng</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>Findings of the Association for Computational Linguistics: ACL 2026</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">979-8-89176-395-1</identifier>
</relatedItem>
<abstract>Evidence-grounded fact-checking requires predicting claim veracity while returning faithful evidence at fine granularity, including exact sentences, table cells, and complete multi-document chains. Although large language models enable decomposition, planning, and multi-agent verification, they can still produce convincing rationales with weak provenance, especially under heterogeneous evidence and multi-hop requirements. We propose GAVEL, a multi-agent debate framework that enforces evidence grounding throughout inference. GAVEL introduces an Evidence Contract that requires debaters to state atomic subclaims and bind each to explicit evidence units, and a Mechanized Chain of Scrutiny in which a neutral Scrutinizer audits outputs and performs deterministic validation of cited identifiers and quoted spans. A Judge then selects a sufficient evidence set and produces the final decision. Experiments on FEVEROUS and HOVER in an open-book setting show that GAVEL improves provenance-aware metrics that jointly require correct labels and correct, complete evidence over strong recent baselines. Ablations confirm that both evidence binding and mechanized citation validation are key to the gains.</abstract>
<identifier type="citekey">xu-etal-2026-gavel</identifier>
<identifier type="doi">10.18653/v1/2026.findings-acl.1789</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.1789/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>35907</start>
<end>35920</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GAVEL: Evidence-Contract Debate with Mechanized Scrutiny for Provenance-Grounded Fact-Checking
%A Xu, Ruoyu
%A Li, Gaoxiang
%A Sheng, Victor S.
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F xu-etal-2026-gavel
%X Evidence-grounded fact-checking requires predicting claim veracity while returning faithful evidence at fine granularity, including exact sentences, table cells, and complete multi-document chains. Although large language models enable decomposition, planning, and multi-agent verification, they can still produce convincing rationales with weak provenance, especially under heterogeneous evidence and multi-hop requirements. We propose GAVEL, a multi-agent debate framework that enforces evidence grounding throughout inference. GAVEL introduces an Evidence Contract that requires debaters to state atomic subclaims and bind each to explicit evidence units, and a Mechanized Chain of Scrutiny in which a neutral Scrutinizer audits outputs and performs deterministic validation of cited identifiers and quoted spans. A Judge then selects a sufficient evidence set and produces the final decision. Experiments on FEVEROUS and HOVER in an open-book setting show that GAVEL improves provenance-aware metrics that jointly require correct labels and correct, complete evidence over strong recent baselines. Ablations confirm that both evidence binding and mechanized citation validation are key to the gains.
%R 10.18653/v1/2026.findings-acl.1789
%U https://aclanthology.org/2026.findings-acl.1789/
%U https://doi.org/10.18653/v1/2026.findings-acl.1789
%P 35907-35920
Markdown (Informal)
[GAVEL: Evidence-Contract Debate with Mechanized Scrutiny for Provenance-Grounded Fact-Checking](https://aclanthology.org/2026.findings-acl.1789/) (Xu et al., Findings 2026)
ACL