Structuring the Unstructured: A Systematic Review of Text-to-Structure Generation for Agentic AI with a Universal Evaluation Framework

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Deng, Zheye, Chan, Chunkit, Zheng, Tianshi, Fan, Wei, Wang, Weiqi, Song, Yangqiu
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909739551555584
author Deng, Zheye
Chan, Chunkit
Zheng, Tianshi
Fan, Wei
Wang, Weiqi
Song, Yangqiu
author_facet Deng, Zheye
Chan, Chunkit
Zheng, Tianshi
Fan, Wei
Wang, Weiqi
Song, Yangqiu
contents The evolution of AI systems toward agentic operation and context-aware retrieval necessitates transforming unstructured text into structured formats like tables, knowledge graphs, and charts. While such conversions enable critical applications from summarization to data mining, current research lacks a comprehensive synthesis of methodologies, datasets, and metrics. This systematic review examines text-to-structure techniques and the encountered challenges, evaluates current datasets and assessment criteria, and outlines potential directions for future research. We also introduce a universal evaluation framework for structured outputs, establishing text-to-structure as foundational infrastructure for next-generation AI systems.
format Preprint
id arxiv_https___arxiv_org_abs_2508_12257
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Structuring the Unstructured: A Systematic Review of Text-to-Structure Generation for Agentic AI with a Universal Evaluation Framework
Deng, Zheye
Chan, Chunkit
Zheng, Tianshi
Fan, Wei
Wang, Weiqi
Song, Yangqiu
Computation and Language
The evolution of AI systems toward agentic operation and context-aware retrieval necessitates transforming unstructured text into structured formats like tables, knowledge graphs, and charts. While such conversions enable critical applications from summarization to data mining, current research lacks a comprehensive synthesis of methodologies, datasets, and metrics. This systematic review examines text-to-structure techniques and the encountered challenges, evaluates current datasets and assessment criteria, and outlines potential directions for future research. We also introduce a universal evaluation framework for structured outputs, establishing text-to-structure as foundational infrastructure for next-generation AI systems.
title Structuring the Unstructured: A Systematic Review of Text-to-Structure Generation for Agentic AI with a Universal Evaluation Framework
topic Computation and Language
url https://arxiv.org/abs/2508.12257