GAVEL: Evidence-Contract Debate with Mechanized Scrutiny for Provenance-Grounded Fact-Checking

Ruoyu Xu, Gaoxiang Li, Victor S. Sheng


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.
Anthology ID:
2026.findings-acl.1789
Volume:
Findings of the Association for Computational Linguistics: ACL 2026
Month:
July
Year:
2026
Address:
San Diego, California, United States
Editors:
Maria Liakata, Viviane P. Moreira, Jiajun Zhang, David Jurgens
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
35907–35920
Language:
URL:
https://aclanthology.org/2026.findings-acl.1789/
DOI:
10.18653/v1/2026.findings-acl.1789
Bibkey:
Cite (ACL):
Ruoyu Xu, Gaoxiang Li, and Victor S. Sheng. 2026. GAVEL: Evidence-Contract Debate with Mechanized Scrutiny for Provenance-Grounded Fact-Checking. In Findings of the Association for Computational Linguistics: ACL 2026, pages 35907–35920, San Diego, California, United States. Association for Computational Linguistics.
Cite (Informal):
GAVEL: Evidence-Contract Debate with Mechanized Scrutiny for Provenance-Grounded Fact-Checking (Xu et al., Findings 2026)
Copy Citation:
PDF:
https://aclanthology.org/2026.findings-acl.1789.pdf
Checklist:
 2026.findings-acl.1789.checklist.pdf