@inproceedings{mathur-etal-2024-matsa,
title = "{MATSA}: Multi-Agent Table Structure Attribution",
author = "Mathur, Puneet and
Siu, Alexa and
Lipka, Nedim and
Sun, Tong",
editor = "Hernandez Farias, Delia Irazu and
Hope, Tom and
Li, Manling",
booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: System Demonstrations",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.emnlp-demo.26",
pages = "250--258",
abstract = "Large Language Models (LLMs) have significantly advanced QA tasks through in-context learning but often suffer from hallucinations. Attributing supporting evidence grounded in source documents has been explored for unstructured text in the past. However, tabular data present unique challenges for attribution due to ambiguities (e.g., abbreviations, domain-specific terms), complex header hierarchies, and the difficulty in interpreting individual table cells without row and column context. We introduce a new task, Fine-grained Structured Table Attribution (FAST-Tab), to generate row and column-level attributions supporting LLM-generated answers. We present MATSA, a novel LLM-based Multi-Agent system capable of post-hoc Table Structure Attribution to help users visually interpret factual claims derived from tables. MATSA augments tabular entities with descriptive context about structure, metadata, and numerical trends to semantically retrieve relevant rows and columns corresponding to facts in an answer. Additionally, we propose TabCite, a diverse benchmark designed to evaluate the FAST-Tab task on tables with complex layouts sourced from Wikipedia and business PDF documents. Extensive experiments demonstrate that MATSA significantly outperforms SOTA baselines on TabCite, achieving an 8-13{\%} improvement in F1 score. Qualitative user studies show that MATSA helps increase user trust in Generative AI by providing enhanced explainability for LLM-assisted table QA and enables professionals to be more productive by saving time on fact-checking LLM-generated answers.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mathur-etal-2024-matsa">
<titleInfo>
<title>MATSA: Multi-Agent Table Structure Attribution</title>
</titleInfo>
<name type="personal">
<namePart type="given">Puneet</namePart>
<namePart type="family">Mathur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexa</namePart>
<namePart type="family">Siu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nedim</namePart>
<namePart type="family">Lipka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Sun</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: System Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Delia</namePart>
<namePart type="given">Irazu</namePart>
<namePart type="family">Hernandez Farias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tom</namePart>
<namePart type="family">Hope</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manling</namePart>
<namePart type="family">Li</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>Large Language Models (LLMs) have significantly advanced QA tasks through in-context learning but often suffer from hallucinations. Attributing supporting evidence grounded in source documents has been explored for unstructured text in the past. However, tabular data present unique challenges for attribution due to ambiguities (e.g., abbreviations, domain-specific terms), complex header hierarchies, and the difficulty in interpreting individual table cells without row and column context. We introduce a new task, Fine-grained Structured Table Attribution (FAST-Tab), to generate row and column-level attributions supporting LLM-generated answers. We present MATSA, a novel LLM-based Multi-Agent system capable of post-hoc Table Structure Attribution to help users visually interpret factual claims derived from tables. MATSA augments tabular entities with descriptive context about structure, metadata, and numerical trends to semantically retrieve relevant rows and columns corresponding to facts in an answer. Additionally, we propose TabCite, a diverse benchmark designed to evaluate the FAST-Tab task on tables with complex layouts sourced from Wikipedia and business PDF documents. Extensive experiments demonstrate that MATSA significantly outperforms SOTA baselines on TabCite, achieving an 8-13% improvement in F1 score. Qualitative user studies show that MATSA helps increase user trust in Generative AI by providing enhanced explainability for LLM-assisted table QA and enables professionals to be more productive by saving time on fact-checking LLM-generated answers.</abstract>
<identifier type="citekey">mathur-etal-2024-matsa</identifier>
<location>
<url>https://aclanthology.org/2024.emnlp-demo.26</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>250</start>
<end>258</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MATSA: Multi-Agent Table Structure Attribution
%A Mathur, Puneet
%A Siu, Alexa
%A Lipka, Nedim
%A Sun, Tong
%Y Hernandez Farias, Delia Irazu
%Y Hope, Tom
%Y Li, Manling
%S Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: System Demonstrations
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F mathur-etal-2024-matsa
%X Large Language Models (LLMs) have significantly advanced QA tasks through in-context learning but often suffer from hallucinations. Attributing supporting evidence grounded in source documents has been explored for unstructured text in the past. However, tabular data present unique challenges for attribution due to ambiguities (e.g., abbreviations, domain-specific terms), complex header hierarchies, and the difficulty in interpreting individual table cells without row and column context. We introduce a new task, Fine-grained Structured Table Attribution (FAST-Tab), to generate row and column-level attributions supporting LLM-generated answers. We present MATSA, a novel LLM-based Multi-Agent system capable of post-hoc Table Structure Attribution to help users visually interpret factual claims derived from tables. MATSA augments tabular entities with descriptive context about structure, metadata, and numerical trends to semantically retrieve relevant rows and columns corresponding to facts in an answer. Additionally, we propose TabCite, a diverse benchmark designed to evaluate the FAST-Tab task on tables with complex layouts sourced from Wikipedia and business PDF documents. Extensive experiments demonstrate that MATSA significantly outperforms SOTA baselines on TabCite, achieving an 8-13% improvement in F1 score. Qualitative user studies show that MATSA helps increase user trust in Generative AI by providing enhanced explainability for LLM-assisted table QA and enables professionals to be more productive by saving time on fact-checking LLM-generated answers.
%U https://aclanthology.org/2024.emnlp-demo.26
%P 250-258
Markdown (Informal)
[MATSA: Multi-Agent Table Structure Attribution](https://aclanthology.org/2024.emnlp-demo.26) (Mathur et al., EMNLP 2024)
ACL
- Puneet Mathur, Alexa Siu, Nedim Lipka, and Tong Sun. 2024. MATSA: Multi-Agent Table Structure Attribution. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 250–258, Miami, Florida, USA. Association for Computational Linguistics.