@inproceedings{park-etal-2026-relevant,
title = "Relevant Is Not Enough: Expert-Audited Decision-Grade Web Evidence for Financial Fact Verification",
author = "Park, Hyunkyung and
Kim, Eui Hyun and
Choi, Wooah and
Zubiaga, Arkaitz",
editor = "Huang, Jimin and
Lee, Yongjae and
Ananiadou, Sophia and
Chen, Hsin-Hsi and
Takamura, Hiroya and
Chen, Chung-Chi",
booktitle = "Proceedings of the 11th Workshop on Financial Technology and Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.finnlp-1.32/",
pages = "394--402",
ISBN = "979-8-89176-466-8",
abstract = "Fact verification systems rank web evidence by relevance, yet relevant passages may lack verdict-critical facts. We define decision-grade evidence as credible, temporally valid, and claim-matched information independently sufficient to support or refute a claim. Using 750 expert-audited claim{--}passage pairs for 150 financial claims, we compare relevance and decision-grade supervision within two rerankers while holding candidate evidence pools and verifiers fixed. Within these pools, 66.5{\%} of relevant pairs are insufficient, and claim-level decision-grade coverage trails relevance coverage by 40.0 percentage points. Compared with relevance supervision, decision-grade supervision improves the ranking of sufficient evidence in one reranker but shows no clear advantage in the other. Frozen (untuned) rerankers remain competitive, and downstream verification gains are modest and input-dependent. Thus, relevance is an unreliable proxy for verdict sufficiency; evidence availability, ordering, and verifier use require separate evaluation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="park-etal-2026-relevant">
<titleInfo>
<title>Relevant Is Not Enough: Expert-Audited Decision-Grade Web Evidence for Financial Fact Verification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hyunkyung</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eui</namePart>
<namePart type="given">Hyun</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wooah</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arkaitz</namePart>
<namePart type="family">Zubiaga</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>Proceedings of the 11th Workshop on Financial Technology and Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jimin</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yongjae</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophia</namePart>
<namePart type="family">Ananiadou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Hsi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hiroya</namePart>
<namePart type="family">Takamura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chung-Chi</namePart>
<namePart type="family">Chen</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">979-8-89176-466-8</identifier>
</relatedItem>
<abstract>Fact verification systems rank web evidence by relevance, yet relevant passages may lack verdict-critical facts. We define decision-grade evidence as credible, temporally valid, and claim-matched information independently sufficient to support or refute a claim. Using 750 expert-audited claim–passage pairs for 150 financial claims, we compare relevance and decision-grade supervision within two rerankers while holding candidate evidence pools and verifiers fixed. Within these pools, 66.5% of relevant pairs are insufficient, and claim-level decision-grade coverage trails relevance coverage by 40.0 percentage points. Compared with relevance supervision, decision-grade supervision improves the ranking of sufficient evidence in one reranker but shows no clear advantage in the other. Frozen (untuned) rerankers remain competitive, and downstream verification gains are modest and input-dependent. Thus, relevance is an unreliable proxy for verdict sufficiency; evidence availability, ordering, and verifier use require separate evaluation.</abstract>
<identifier type="citekey">park-etal-2026-relevant</identifier>
<location>
<url>https://aclanthology.org/2026.finnlp-1.32/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>394</start>
<end>402</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Relevant Is Not Enough: Expert-Audited Decision-Grade Web Evidence for Financial Fact Verification
%A Park, Hyunkyung
%A Kim, Eui Hyun
%A Choi, Wooah
%A Zubiaga, Arkaitz
%Y Huang, Jimin
%Y Lee, Yongjae
%Y Ananiadou, Sophia
%Y Chen, Hsin-Hsi
%Y Takamura, Hiroya
%Y Chen, Chung-Chi
%S Proceedings of the 11th Workshop on Financial Technology and Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-466-8
%F park-etal-2026-relevant
%X Fact verification systems rank web evidence by relevance, yet relevant passages may lack verdict-critical facts. We define decision-grade evidence as credible, temporally valid, and claim-matched information independently sufficient to support or refute a claim. Using 750 expert-audited claim–passage pairs for 150 financial claims, we compare relevance and decision-grade supervision within two rerankers while holding candidate evidence pools and verifiers fixed. Within these pools, 66.5% of relevant pairs are insufficient, and claim-level decision-grade coverage trails relevance coverage by 40.0 percentage points. Compared with relevance supervision, decision-grade supervision improves the ranking of sufficient evidence in one reranker but shows no clear advantage in the other. Frozen (untuned) rerankers remain competitive, and downstream verification gains are modest and input-dependent. Thus, relevance is an unreliable proxy for verdict sufficiency; evidence availability, ordering, and verifier use require separate evaluation.
%U https://aclanthology.org/2026.finnlp-1.32/
%P 394-402
Markdown (Informal)
[Relevant Is Not Enough: Expert-Audited Decision-Grade Web Evidence for Financial Fact Verification](https://aclanthology.org/2026.finnlp-1.32/) (Park et al., FinNLP 2026)
ACL