@inproceedings{tang-etal-2024-m3d,
title = "{M}3{D}: {M}ulti{M}odal {M}ulti{D}ocument Fine-Grained Inconsistency Detection",
author = "Tang, Chia-Wei and
Chen, Ting-Chih and
Nguyen, Kiet and
Mehrab, Kazi Sajeed and
Ishmam, Alvi and
Thomas, Chris",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.emnlp-main.1243",
pages = "22270--22293",
abstract = "Fact-checking claims is a highly laborious task that involves understanding how each factual assertion within the claim relates to a set of trusted source materials. Existing approaches make sample-level predictions but fail to identify the specific aspects of the claim that are troublesome and the specific evidence relied upon. In this paper, we introduce a method and new benchmark for this challenging task. Our method predicts the fine-grained logical relationship of each aspect of the claim from a set of multimodal documents, which include text, image(s), video(s), and audio(s). We also introduce a new benchmark (M3DC) of claims requiring multimodal multidocument reasoning, which we construct using a novel claim synthesis technique. Experiments show that our approach outperforms other models on this challenging task on two benchmarks while providing finer-grained predictions, explanations, and evidence.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tang-etal-2024-m3d">
<titleInfo>
<title>M3D: MultiModal MultiDocument Fine-Grained Inconsistency Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chia-Wei</namePart>
<namePart type="family">Tang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ting-Chih</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kiet</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kazi</namePart>
<namePart type="given">Sajeed</namePart>
<namePart type="family">Mehrab</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alvi</namePart>
<namePart type="family">Ishmam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Thomas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</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">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Fact-checking claims is a highly laborious task that involves understanding how each factual assertion within the claim relates to a set of trusted source materials. Existing approaches make sample-level predictions but fail to identify the specific aspects of the claim that are troublesome and the specific evidence relied upon. In this paper, we introduce a method and new benchmark for this challenging task. Our method predicts the fine-grained logical relationship of each aspect of the claim from a set of multimodal documents, which include text, image(s), video(s), and audio(s). We also introduce a new benchmark (M3DC) of claims requiring multimodal multidocument reasoning, which we construct using a novel claim synthesis technique. Experiments show that our approach outperforms other models on this challenging task on two benchmarks while providing finer-grained predictions, explanations, and evidence.</abstract>
<identifier type="citekey">tang-etal-2024-m3d</identifier>
<location>
<url>https://aclanthology.org/2024.emnlp-main.1243</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>22270</start>
<end>22293</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T M3D: MultiModal MultiDocument Fine-Grained Inconsistency Detection
%A Tang, Chia-Wei
%A Chen, Ting-Chih
%A Nguyen, Kiet
%A Mehrab, Kazi Sajeed
%A Ishmam, Alvi
%A Thomas, Chris
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F tang-etal-2024-m3d
%X Fact-checking claims is a highly laborious task that involves understanding how each factual assertion within the claim relates to a set of trusted source materials. Existing approaches make sample-level predictions but fail to identify the specific aspects of the claim that are troublesome and the specific evidence relied upon. In this paper, we introduce a method and new benchmark for this challenging task. Our method predicts the fine-grained logical relationship of each aspect of the claim from a set of multimodal documents, which include text, image(s), video(s), and audio(s). We also introduce a new benchmark (M3DC) of claims requiring multimodal multidocument reasoning, which we construct using a novel claim synthesis technique. Experiments show that our approach outperforms other models on this challenging task on two benchmarks while providing finer-grained predictions, explanations, and evidence.
%U https://aclanthology.org/2024.emnlp-main.1243
%P 22270-22293
Markdown (Informal)
[M3D: MultiModal MultiDocument Fine-Grained Inconsistency Detection](https://aclanthology.org/2024.emnlp-main.1243) (Tang et al., EMNLP 2024)
ACL
- Chia-Wei Tang, Ting-Chih Chen, Kiet Nguyen, Kazi Sajeed Mehrab, Alvi Ishmam, and Chris Thomas. 2024. M3D: MultiModal MultiDocument Fine-Grained Inconsistency Detection. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 22270–22293, Miami, Florida, USA. Association for Computational Linguistics.