@inproceedings{yang-etal-2026-mtimefact,
title = "{MTIMEFACT}: Improving Large Language Models for Multi-Hop Temporal Fact-Checking",
author = "Yang, Xinwei and
Guo, Ruiling and
Huang, Chen and
Lei, Wenqiang and
Ng, See-Kiong",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.979/",
pages = "22592--22614",
ISBN = "979-8-89176-459-0",
abstract = "Real-world fact-checking faces the challenge of temporal dynamics, where misinformation manifests as evolving evidences rather than static claims. Verifying such claims necessitates the synthesis of multi-hop fragmented evidence dispersed across the timeline. However, existing benchmarks largely neglect this complexity, limiting evaluation to static settings that fail to capture real-world demands. To address this, we pioneer MTIMEFACTCHECK, the first dynamic benchmark to rigorously evaluate multi-hop temporal fact-checking in realistic, evolving contexts. Utilizing MTIMEFACTCHECK, we curate the MTimeFactCorpus dataset to benchmark sixteen LLM baselines, scrutinizing their capabilities and critical limitations. Building on these findings, we tentatively propose a novel method MTIMEFACTCHECK to augment LLM efficacy in multi-hop temporal fact-checking, offering guidance for future research. Our data and code are available at \url{https://github.com/SCUNLP/MTimeFact}."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-etal-2026-mtimefact">
<titleInfo>
<title>MTIMEFACT: Improving Large Language Models for Multi-Hop Temporal Fact-Checking</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xinwei</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruiling</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chen</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenqiang</namePart>
<namePart type="family">Lei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">See-Kiong</namePart>
<namePart type="family">Ng</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 2026 Conference on Empirical Methods in Natural Language Processing</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">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>Real-world fact-checking faces the challenge of temporal dynamics, where misinformation manifests as evolving evidences rather than static claims. Verifying such claims necessitates the synthesis of multi-hop fragmented evidence dispersed across the timeline. However, existing benchmarks largely neglect this complexity, limiting evaluation to static settings that fail to capture real-world demands. To address this, we pioneer MTIMEFACTCHECK, the first dynamic benchmark to rigorously evaluate multi-hop temporal fact-checking in realistic, evolving contexts. Utilizing MTIMEFACTCHECK, we curate the MTimeFactCorpus dataset to benchmark sixteen LLM baselines, scrutinizing their capabilities and critical limitations. Building on these findings, we tentatively propose a novel method MTIMEFACTCHECK to augment LLM efficacy in multi-hop temporal fact-checking, offering guidance for future research. Our data and code are available at https://github.com/SCUNLP/MTimeFact.</abstract>
<identifier type="citekey">yang-etal-2026-mtimefact</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.979/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>22592</start>
<end>22614</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MTIMEFACT: Improving Large Language Models for Multi-Hop Temporal Fact-Checking
%A Yang, Xinwei
%A Guo, Ruiling
%A Huang, Chen
%A Lei, Wenqiang
%A Ng, See-Kiong
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F yang-etal-2026-mtimefact
%X Real-world fact-checking faces the challenge of temporal dynamics, where misinformation manifests as evolving evidences rather than static claims. Verifying such claims necessitates the synthesis of multi-hop fragmented evidence dispersed across the timeline. However, existing benchmarks largely neglect this complexity, limiting evaluation to static settings that fail to capture real-world demands. To address this, we pioneer MTIMEFACTCHECK, the first dynamic benchmark to rigorously evaluate multi-hop temporal fact-checking in realistic, evolving contexts. Utilizing MTIMEFACTCHECK, we curate the MTimeFactCorpus dataset to benchmark sixteen LLM baselines, scrutinizing their capabilities and critical limitations. Building on these findings, we tentatively propose a novel method MTIMEFACTCHECK to augment LLM efficacy in multi-hop temporal fact-checking, offering guidance for future research. Our data and code are available at https://github.com/SCUNLP/MTimeFact.
%U https://aclanthology.org/2026.emnlp-main.979/
%P 22592-22614
Markdown (Informal)
[MTIMEFACT: Improving Large Language Models for Multi-Hop Temporal Fact-Checking](https://aclanthology.org/2026.emnlp-main.979/) (Yang et al., EMNLP 2026)
ACL