Schema-Driven Information Extraction from Heterogeneous Tables

arXiv:2305.14336v3 Announce Type: replace
Abstract: In this paper, we explore the question of whether large language models can support cost-efficient information extraction from tables. We introduce schema-driven information extraction, a new task that transforms tabular data into structured records following a human-authored schema. To assess various LLM's capabilities on this task, we present a benchmark comprised of tables from four diverse domains: machine learning papers, chemistry literature, material science journals, and webpages. We use this collection of annotated tables to …

abstract arxiv capabilities cost cs.cl data explore extraction human information information extraction language language models large language large language models llm paper question records schema support tables tabular tabular data type