# Schema-Driven Information Extraction from Heterogeneous Tables Source: [Schema-Driven Information Extraction from Heterogeneous Tables]() Collection index: [llms.txt]() Data updated: 2026-01-04T04:12:38.378Z Authors: Fan Bai, Junmo Kang, Gabriel Stanovsky, Dayne Freitag, Mark Dredze, Alan Ritter Published: 2023-05-23T17:58:10.000Z ## 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 evaluate the ability of open-source and API-based language models to extract information from tables covering diverse domains and data formats. Our experiments demonstrate that surprisingly competitive performance can be achieved without requiring task-specific pipelines or labels, achieving F1 scores ranging from 74.2 to 96.1, while maintaining cost efficiency. Moreover, through detailed ablation studies and analyses, we investigate the factors contributing to model success and validate the practicality of distilling compact models to reduce API reliance. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Leaderboard Extraction on PWC LEADERBOARDS](): Leaderboard Extraction; PWC LEADERBOARDS; Micro Precision: 23.9. ## Original sources and implementation [Original paper]() [PDF]() [Implementation]()