E5: Zero-shot Hierarchical Table Analysis using Augmented LLMs via Explain, Extract, Execute, Exhibit and Extrapolate

Zhehao Zhang, Yan Gao, Jian-Guang Lou


Abstract
Analyzing large hierarchical tables with multi-level headers presents challenges due to their complex structure, implicit semantics, and calculation relationships. While recent advancements in large language models (LLMs) have shown promise in flat table analysis, their application to hierarchical tables is constrained by the reliance on manually curated exemplars and the model’s token capacity limitations. Addressing these challenges, we introduce a novel code-augmented LLM-based framework, E5, for zero-shot hierarchical table question answering. This approach encompasses self-explaining the table’s hierarchical structures, code generation to extract relevant information and apply operations, external code execution to prevent hallucinations, and leveraging LLMs’ reasoning for final answer derivation. Empirical results indicate that our method, based on GPT-4, outperforms state-of-the-art fine-tuning methods with a 44.38 Exact Match improvement. Furthermore, we present F3, an adaptive algorithm designed for token-limited scenarios, effectively condensing large tables while maintaining useful information. Our experiments prove its efficiency, enabling the processing of large tables even with models having limited context lengths. The code is available at https://github.com/zzh-SJTU/E5-Hierarchical-Table-Analysis.
Anthology ID:
2024.naacl-long.68
Volume:
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Kevin Duh, Helena Gomez, Steven Bethard
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1244–1258
Language:
URL:
https://aclanthology.org/2024.naacl-long.68
DOI:
Bibkey:
Cite (ACL):
Zhehao Zhang, Yan Gao, and Jian-Guang Lou. 2024. E5: Zero-shot Hierarchical Table Analysis using Augmented LLMs via Explain, Extract, Execute, Exhibit and Extrapolate. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 1244–1258, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
E5: Zero-shot Hierarchical Table Analysis using Augmented LLMs via Explain, Extract, Execute, Exhibit and Extrapolate (Zhang et al., NAACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.naacl-long.68.pdf
Copyright:
 2024.naacl-long.68.copyright.pdf