@inproceedings{jiang-etal-2026-glisters,
title = "All That Glisters Is Not Gold: A Benchmark for Reference-Free Counterfactual Financial Misinformation Detection",
author = "Jiang, Yuechen and
Liu, Zhiwei and
Cao, Yupeng and
He, Yueru and
Xu, Ziyang and
Xu, Chen and
Deng, Zhiyang and
Tiwari, Prayag and
Chen, Xi and
Lopez-Lira, Alejandro and
Huang, Jimin and
Tsujii, Junichi and
Ananiadou, Sophia",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-long.492/",
pages = "10737--10776",
ISBN = "979-8-89176-390-6",
abstract = "We introduce RFC-Bench, a benchmark for evaluating large language models on financial misinformation under realistic news. RFC-Bench operates at the paragraph level and captures the contextual complexity of financial news where meaning emerges from dispersed cues. The benchmark defines two complementary tasks: reference-free misinformation detection and comparison-based diagnosis using paired original{--}perturbed inputs. Experiments reveal a consistent pattern: performance is substantially stronger when comparative context is available, while reference-free settings expose significant weaknesses, including unstable predictions and elevated invalid outputs. These results indicate that current models struggle to maintain coherent belief states without external grounding. By highlighting this gap, RFC-Bench provides a structured testbed for studying reference-free reasoning and advancing more reliable financial misinformation detection in real-world settings."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jiang-etal-2026-glisters">
<titleInfo>
<title>All That Glisters Is Not Gold: A Benchmark for Reference-Free Counterfactual Financial Misinformation Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuechen</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiwei</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yupeng</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yueru</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ziyang</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chen</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiyang</namePart>
<namePart type="family">Deng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Prayag</namePart>
<namePart type="family">Tiwari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alejandro</namePart>
<namePart type="family">Lopez-Lira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jimin</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junichi</namePart>
<namePart type="family">Tsujii</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophia</namePart>
<namePart type="family">Ananiadou</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>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</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">979-8-89176-390-6</identifier>
</relatedItem>
<abstract>We introduce RFC-Bench, a benchmark for evaluating large language models on financial misinformation under realistic news. RFC-Bench operates at the paragraph level and captures the contextual complexity of financial news where meaning emerges from dispersed cues. The benchmark defines two complementary tasks: reference-free misinformation detection and comparison-based diagnosis using paired original–perturbed inputs. Experiments reveal a consistent pattern: performance is substantially stronger when comparative context is available, while reference-free settings expose significant weaknesses, including unstable predictions and elevated invalid outputs. These results indicate that current models struggle to maintain coherent belief states without external grounding. By highlighting this gap, RFC-Bench provides a structured testbed for studying reference-free reasoning and advancing more reliable financial misinformation detection in real-world settings.</abstract>
<identifier type="citekey">jiang-etal-2026-glisters</identifier>
<location>
<url>https://aclanthology.org/2026.acl-long.492/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>10737</start>
<end>10776</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T All That Glisters Is Not Gold: A Benchmark for Reference-Free Counterfactual Financial Misinformation Detection
%A Jiang, Yuechen
%A Liu, Zhiwei
%A Cao, Yupeng
%A He, Yueru
%A Xu, Ziyang
%A Xu, Chen
%A Deng, Zhiyang
%A Tiwari, Prayag
%A Chen, Xi
%A Lopez-Lira, Alejandro
%A Huang, Jimin
%A Tsujii, Junichi
%A Ananiadou, Sophia
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-390-6
%F jiang-etal-2026-glisters
%X We introduce RFC-Bench, a benchmark for evaluating large language models on financial misinformation under realistic news. RFC-Bench operates at the paragraph level and captures the contextual complexity of financial news where meaning emerges from dispersed cues. The benchmark defines two complementary tasks: reference-free misinformation detection and comparison-based diagnosis using paired original–perturbed inputs. Experiments reveal a consistent pattern: performance is substantially stronger when comparative context is available, while reference-free settings expose significant weaknesses, including unstable predictions and elevated invalid outputs. These results indicate that current models struggle to maintain coherent belief states without external grounding. By highlighting this gap, RFC-Bench provides a structured testbed for studying reference-free reasoning and advancing more reliable financial misinformation detection in real-world settings.
%U https://aclanthology.org/2026.acl-long.492/
%P 10737-10776
Markdown (Informal)
[All That Glisters Is Not Gold: A Benchmark for Reference-Free Counterfactual Financial Misinformation Detection](https://aclanthology.org/2026.acl-long.492/) (Jiang et al., ACL 2026)
ACL
- Yuechen Jiang, Zhiwei Liu, Yupeng Cao, Yueru He, Ziyang Xu, Chen Xu, Zhiyang Deng, Prayag Tiwari, Xi Chen, Alejandro Lopez-Lira, Jimin Huang, Junichi Tsujii, and Sophia Ananiadou. 2026. All That Glisters Is Not Gold: A Benchmark for Reference-Free Counterfactual Financial Misinformation Detection. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 10737–10776, San Diego, California, United States. Association for Computational Linguistics.