LLM driven Text-to-Table Generation through Sub-Tasks Guidance and Iterative Refinement

TL;DR

This paper introduces a novel LLM-driven text-to-table generation system that uses task decomposition and iterative refinement to improve structured data extraction from unstructured text, addressing challenges like ambiguity and reasoning.

Contribution

The paper presents a new prompting approach combining sub-task guidance and iterative self-feedback to enhance text-to-table generation quality with improved accuracy and robustness.

Findings

Outperforms baseline methods on two public datasets.

Task decomposition improves table generation accuracy.

Iterative refinement enhances table quality but increases computational cost.

Abstract

Transforming unstructured text into structured data is a complex task, requiring semantic understanding, reasoning, and structural comprehension. While Large Language Models (LLMs) offer potential, they often struggle with handling ambiguous or domain-specific data, maintaining table structure, managing long inputs, and addressing numerical reasoning. This paper proposes an efficient system for LLM-driven text-to-table generation that leverages novel prompting techniques. Specifically, the system incorporates two key strategies: breaking down the text-to-table task into manageable, guided sub-tasks and refining the generated tables through iterative self-feedback. We show that this custom task decomposition allows the model to address the problem in a stepwise manner and improves the quality of the generated table. Furthermore, we discuss the benefits and potential risks associated with iterative self-feedback on the generated tables while highlighting the trade-offs between enhanced performance and computational cost. Our methods achieve strong results compared to baselines on two complex text-to-table generation datasets available in the public domain.