@inproceedings{yu-etal-2026-erga,
title = "{ERGA}: An Explorer{--}Refiner Game with Backdoor-Adjusted Verdict Aggregation for {LLM}-based Claim Verification",
author = "Yu, Wanlong and
Liu, Feng and
Tian, Zhiliang and
Huang, Zhen and
Wang, Yonghui and
Huang, Jingyuan and
Li, Dongsheng",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.2113/",
pages = "45048--45066",
ISBN = "979-8-89176-462-0",
abstract = "LLM-based fact-checking verifies complex claims through decomposition, retrieval, and reasoning aggregation. Existing methods expand verification inputs to cover more factual conditions, but added fragments can be redundant or misleading, compete with decisive evidence, and bias predictions toward surface relevance. Debiasing methods mitigate this bias by estimating shortcut effects from claim-side cues or biased signals in constructed inputs. However, because they calibrate verifier predictions after input construction, they are not designed to repair missing or noisy verification states. Thus, complex fact-checking should balance factual coverage and noise control during verification-state construction. We propose ERGA, an Explorer{--}Refiner Game with Backdoor-Adjusted Verdict Aggregation. ERGA formulates verification as editable state construction, initializing the state from decomposed verification units, retrieved evidence, and local analyses. It then runs an adversarial Explorer{--}Refiner game over this state: the Explorer strengthens under-covered factual signals, while the Refiner merges redundancy and separates weak or misleading fragments. Through this game interaction, ERGA obtains a refined state with a better coverage{--}noise balance and a removed fragment record. For verdict aggregation, ERGA uses the removed-fragment record to condition verifier predictions and aggregates them in a backdoor-adjusted form to reduce residual shortcut effects. Experiments on HoVer and FEVEROUS-S show that ERGA outperforms strong baselines."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yu-etal-2026-erga">
<titleInfo>
<title>ERGA: An Explorer–Refiner Game with Backdoor-Adjusted Verdict Aggregation for LLM-based Claim Verification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanlong</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Feng</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiliang</namePart>
<namePart type="family">Tian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhen</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yonghui</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jingyuan</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dongsheng</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>LLM-based fact-checking verifies complex claims through decomposition, retrieval, and reasoning aggregation. Existing methods expand verification inputs to cover more factual conditions, but added fragments can be redundant or misleading, compete with decisive evidence, and bias predictions toward surface relevance. Debiasing methods mitigate this bias by estimating shortcut effects from claim-side cues or biased signals in constructed inputs. However, because they calibrate verifier predictions after input construction, they are not designed to repair missing or noisy verification states. Thus, complex fact-checking should balance factual coverage and noise control during verification-state construction. We propose ERGA, an Explorer–Refiner Game with Backdoor-Adjusted Verdict Aggregation. ERGA formulates verification as editable state construction, initializing the state from decomposed verification units, retrieved evidence, and local analyses. It then runs an adversarial Explorer–Refiner game over this state: the Explorer strengthens under-covered factual signals, while the Refiner merges redundancy and separates weak or misleading fragments. Through this game interaction, ERGA obtains a refined state with a better coverage–noise balance and a removed fragment record. For verdict aggregation, ERGA uses the removed-fragment record to condition verifier predictions and aggregates them in a backdoor-adjusted form to reduce residual shortcut effects. Experiments on HoVer and FEVEROUS-S show that ERGA outperforms strong baselines.</abstract>
<identifier type="citekey">yu-etal-2026-erga</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.2113/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>45048</start>
<end>45066</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ERGA: An Explorer–Refiner Game with Backdoor-Adjusted Verdict Aggregation for LLM-based Claim Verification
%A Yu, Wanlong
%A Liu, Feng
%A Tian, Zhiliang
%A Huang, Zhen
%A Wang, Yonghui
%A Huang, Jingyuan
%A Li, Dongsheng
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F yu-etal-2026-erga
%X LLM-based fact-checking verifies complex claims through decomposition, retrieval, and reasoning aggregation. Existing methods expand verification inputs to cover more factual conditions, but added fragments can be redundant or misleading, compete with decisive evidence, and bias predictions toward surface relevance. Debiasing methods mitigate this bias by estimating shortcut effects from claim-side cues or biased signals in constructed inputs. However, because they calibrate verifier predictions after input construction, they are not designed to repair missing or noisy verification states. Thus, complex fact-checking should balance factual coverage and noise control during verification-state construction. We propose ERGA, an Explorer–Refiner Game with Backdoor-Adjusted Verdict Aggregation. ERGA formulates verification as editable state construction, initializing the state from decomposed verification units, retrieved evidence, and local analyses. It then runs an adversarial Explorer–Refiner game over this state: the Explorer strengthens under-covered factual signals, while the Refiner merges redundancy and separates weak or misleading fragments. Through this game interaction, ERGA obtains a refined state with a better coverage–noise balance and a removed fragment record. For verdict aggregation, ERGA uses the removed-fragment record to condition verifier predictions and aggregates them in a backdoor-adjusted form to reduce residual shortcut effects. Experiments on HoVer and FEVEROUS-S show that ERGA outperforms strong baselines.
%U https://aclanthology.org/2026.findings-emnlp.2113/
%P 45048-45066
Markdown (Informal)
[ERGA: An Explorer–Refiner Game with Backdoor-Adjusted Verdict Aggregation for LLM-based Claim Verification](https://aclanthology.org/2026.findings-emnlp.2113/) (Yu et al., Findings 2026)
ACL