MATSA: Multi-Agent Table Structure Attribution

Puneet Mathur, Alexa Siu, Nedim Lipka, Tong Sun


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.
Anthology ID:
2024.emnlp-demo.26
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: System Demonstrations
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Delia Irazu Hernandez Farias, Tom Hope, Manling Li
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
250–258
Language:
URL:
https://aclanthology.org/2024.emnlp-demo.26
DOI:
Bibkey:
Cite (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.
Cite (Informal):
MATSA: Multi-Agent Table Structure Attribution (Mathur et al., EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-demo.26.pdf