Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2508.08653 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909733918605312 |
|---|---|
| author | C, Rajmohan Harne, Sarthak Agarwal, Arvind |
| author_facet | C, Rajmohan Harne, Sarthak Agarwal, Arvind |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_08653 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LLM driven Text-to-Table Generation through Sub-Tasks Guidance and Iterative Refinement C, Rajmohan Harne, Sarthak Agarwal, Arvind Computation and Language Artificial Intelligence 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. |
| title | LLM driven Text-to-Table Generation through Sub-Tasks Guidance and Iterative Refinement |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2508.08653 |