@inproceedings{kong-etal-2026-reflex,
title = "{REFLEX}: Self-Refining Explainable Fact-Checking via Verdict-Anchored Style Control",
author = "Kong, Chuyi and
Gao, Wei and
Ma, Jing and
Lin, Hongzhan and
Sun, Yuxi",
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.202/",
pages = "4403--4431",
ISBN = "979-8-89176-390-6",
abstract = "The prevalence of fake news on social media calls for automated fact-checking systems that deliver not only accurate verdicts but also faithful explanations. However, existing large language model (LLM)-based methods often overlook deceptive misinformation styles in generated explanations, producing unfaithful rationales that may mislead human judgment. They also rely heavily on external knowledge sources, which can introduce hallucinations and incur substantial latency, undermining both reliability and responsiveness in real-time settings. To address these limitations, we propose REason-guided Fact-checking with Latent EXplanations (REFLEX), a self-refining framework that explicitly controls reasoning style by anchoring explanations to the predicted verdict. REFLEX leverages self-disagreement veracity signals between a backbone model and its fine-tuned variant to construct steering vectors, thereby naturally disentangling factual content from stylistic cues. Experiments on a real-world benchmark show that REFLEX achieves state-of-the-art performance under LLaMA-series models using only 465 self-refined samples. Owing to its transferability, REFLEX also yields gains of up to 7.54 Macro-F1 points on in-the-wild data. Further analysis shows that our method effectively mitigates faithful hallucination, leading to both more reliable explanations and more accurate verdicts than prior explainable fact-checking approaches."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kong-etal-2026-reflex">
<titleInfo>
<title>REFLEX: Self-Refining Explainable Fact-Checking via Verdict-Anchored Style Control</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chuyi</namePart>
<namePart type="family">Kong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongzhan</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuxi</namePart>
<namePart type="family">Sun</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>The prevalence of fake news on social media calls for automated fact-checking systems that deliver not only accurate verdicts but also faithful explanations. However, existing large language model (LLM)-based methods often overlook deceptive misinformation styles in generated explanations, producing unfaithful rationales that may mislead human judgment. They also rely heavily on external knowledge sources, which can introduce hallucinations and incur substantial latency, undermining both reliability and responsiveness in real-time settings. To address these limitations, we propose REason-guided Fact-checking with Latent EXplanations (REFLEX), a self-refining framework that explicitly controls reasoning style by anchoring explanations to the predicted verdict. REFLEX leverages self-disagreement veracity signals between a backbone model and its fine-tuned variant to construct steering vectors, thereby naturally disentangling factual content from stylistic cues. Experiments on a real-world benchmark show that REFLEX achieves state-of-the-art performance under LLaMA-series models using only 465 self-refined samples. Owing to its transferability, REFLEX also yields gains of up to 7.54 Macro-F1 points on in-the-wild data. Further analysis shows that our method effectively mitigates faithful hallucination, leading to both more reliable explanations and more accurate verdicts than prior explainable fact-checking approaches.</abstract>
<identifier type="citekey">kong-etal-2026-reflex</identifier>
<location>
<url>https://aclanthology.org/2026.acl-long.202/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>4403</start>
<end>4431</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T REFLEX: Self-Refining Explainable Fact-Checking via Verdict-Anchored Style Control
%A Kong, Chuyi
%A Gao, Wei
%A Ma, Jing
%A Lin, Hongzhan
%A Sun, Yuxi
%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 kong-etal-2026-reflex
%X The prevalence of fake news on social media calls for automated fact-checking systems that deliver not only accurate verdicts but also faithful explanations. However, existing large language model (LLM)-based methods often overlook deceptive misinformation styles in generated explanations, producing unfaithful rationales that may mislead human judgment. They also rely heavily on external knowledge sources, which can introduce hallucinations and incur substantial latency, undermining both reliability and responsiveness in real-time settings. To address these limitations, we propose REason-guided Fact-checking with Latent EXplanations (REFLEX), a self-refining framework that explicitly controls reasoning style by anchoring explanations to the predicted verdict. REFLEX leverages self-disagreement veracity signals between a backbone model and its fine-tuned variant to construct steering vectors, thereby naturally disentangling factual content from stylistic cues. Experiments on a real-world benchmark show that REFLEX achieves state-of-the-art performance under LLaMA-series models using only 465 self-refined samples. Owing to its transferability, REFLEX also yields gains of up to 7.54 Macro-F1 points on in-the-wild data. Further analysis shows that our method effectively mitigates faithful hallucination, leading to both more reliable explanations and more accurate verdicts than prior explainable fact-checking approaches.
%U https://aclanthology.org/2026.acl-long.202/
%P 4403-4431
Markdown (Informal)
[REFLEX: Self-Refining Explainable Fact-Checking via Verdict-Anchored Style Control](https://aclanthology.org/2026.acl-long.202/) (Kong et al., ACL 2026)
ACL