@inproceedings{ran-etal-2025-bisaga,
title = "{B}i{S}a{GA}: A Novel Bidirectional Sparse Graph Attention Adapter for Evidence-Based Fact-Checking",
author = "Ran, Junfeng and
Luo, Weiyao and
Tian, Zailong and
Zhao, Guangxiang and
Zhu, Dawei and
Wu, Longyun and
Huang, Hailiang and
Li, Sujian",
editor = "Sun, Maosong and
Duan, Peiyong and
Liu, Zhiyuan and
Xu, Ruifeng and
Sun, Weiwei",
booktitle = "Proceedings of the 24th {C}hina National Conference on Computational Linguistics ({CCL} 2025)",
month = aug,
year = "2025",
address = "Jinan, China",
publisher = "Chinese Information Processing Society of China",
url = "https://aclanthology.org/2025.ccl-1.72/",
pages = "946--959",
abstract = "``Evidence-based fact-checking aims to verify or debunk claims using evidence and has greatly benefited from advancements in Large Language Models (LLMs). This task relies on clarify-ing and discriminating relations between entities. However, autoregressive LLMs struggle with understanding relations presented in different orders or narratives, as their unidirectional na-ture hampers effective performance. To address this challenge, we propose a novel method that leverages bidirectional attention as an external adapter to facilitate two-way information aggregation. Additionally, we employ hierarchical sparse graphs to merge local and global information and introduce an efficient feature-compression technique to minimize the number of adapter parameters. Experimental results on both English and Chinese datasets demonstrate the significant improvements achieved by our approach, showcasing state-of-the-art performance in the evidence-based fact-checking task.''"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ran-etal-2025-bisaga">
<titleInfo>
<title>BiSaGA: A Novel Bidirectional Sparse Graph Attention Adapter for Evidence-Based Fact-Checking</title>
</titleInfo>
<name type="personal">
<namePart type="given">Junfeng</namePart>
<namePart type="family">Ran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weiyao</namePart>
<namePart type="family">Luo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zailong</namePart>
<namePart type="family">Tian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guangxiang</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dawei</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Longyun</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hailiang</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sujian</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 24th China National Conference on Computational Linguistics (CCL 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maosong</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peiyong</namePart>
<namePart type="family">Duan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiyuan</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruifeng</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weiwei</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Chinese Information Processing Society of China</publisher>
<place>
<placeTerm type="text">Jinan, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>“Evidence-based fact-checking aims to verify or debunk claims using evidence and has greatly benefited from advancements in Large Language Models (LLMs). This task relies on clarify-ing and discriminating relations between entities. However, autoregressive LLMs struggle with understanding relations presented in different orders or narratives, as their unidirectional na-ture hampers effective performance. To address this challenge, we propose a novel method that leverages bidirectional attention as an external adapter to facilitate two-way information aggregation. Additionally, we employ hierarchical sparse graphs to merge local and global information and introduce an efficient feature-compression technique to minimize the number of adapter parameters. Experimental results on both English and Chinese datasets demonstrate the significant improvements achieved by our approach, showcasing state-of-the-art performance in the evidence-based fact-checking task.”</abstract>
<identifier type="citekey">ran-etal-2025-bisaga</identifier>
<location>
<url>https://aclanthology.org/2025.ccl-1.72/</url>
</location>
<part>
<date>2025-08</date>
<extent unit="page">
<start>946</start>
<end>959</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BiSaGA: A Novel Bidirectional Sparse Graph Attention Adapter for Evidence-Based Fact-Checking
%A Ran, Junfeng
%A Luo, Weiyao
%A Tian, Zailong
%A Zhao, Guangxiang
%A Zhu, Dawei
%A Wu, Longyun
%A Huang, Hailiang
%A Li, Sujian
%Y Sun, Maosong
%Y Duan, Peiyong
%Y Liu, Zhiyuan
%Y Xu, Ruifeng
%Y Sun, Weiwei
%S Proceedings of the 24th China National Conference on Computational Linguistics (CCL 2025)
%D 2025
%8 August
%I Chinese Information Processing Society of China
%C Jinan, China
%F ran-etal-2025-bisaga
%X “Evidence-based fact-checking aims to verify or debunk claims using evidence and has greatly benefited from advancements in Large Language Models (LLMs). This task relies on clarify-ing and discriminating relations between entities. However, autoregressive LLMs struggle with understanding relations presented in different orders or narratives, as their unidirectional na-ture hampers effective performance. To address this challenge, we propose a novel method that leverages bidirectional attention as an external adapter to facilitate two-way information aggregation. Additionally, we employ hierarchical sparse graphs to merge local and global information and introduce an efficient feature-compression technique to minimize the number of adapter parameters. Experimental results on both English and Chinese datasets demonstrate the significant improvements achieved by our approach, showcasing state-of-the-art performance in the evidence-based fact-checking task.”
%U https://aclanthology.org/2025.ccl-1.72/
%P 946-959
Markdown (Informal)
[BiSaGA: A Novel Bidirectional Sparse Graph Attention Adapter for Evidence-Based Fact-Checking](https://aclanthology.org/2025.ccl-1.72/) (Ran et al., CCL 2025)
ACL
- Junfeng Ran, Weiyao Luo, Zailong Tian, Guangxiang Zhao, Dawei Zhu, Longyun Wu, Hailiang Huang, and Sujian Li. 2025. BiSaGA: A Novel Bidirectional Sparse Graph Attention Adapter for Evidence-Based Fact-Checking. In Proceedings of the 24th China National Conference on Computational Linguistics (CCL 2025), pages 946–959, Jinan, China. Chinese Information Processing Society of China.