LLM driven Text-to-Table Generation through Sub-Tasks Guidance and Iterative Refinement
This addresses the challenge of text-to-table generation for data processing applications, but it is incremental as it builds on existing LLM methods with novel prompting techniques.
The paper tackles the problem of transforming unstructured text into structured tables using LLMs, which often struggle with ambiguity and structure, by proposing a system that uses guided sub-tasks and iterative refinement, achieving strong results on two public datasets.
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.