{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/schema-driven-information-extraction-from","title":"Schema-Driven Information Extraction from Heterogeneous Tables","arxiv_id":"2305.14336","date":"2023-05-23","proceeding":null,"authors":["Fan Bai","Junmo Kang","Gabriel Stanovsky","Dayne Freitag","Mark Dredze","Alan Ritter"],"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.","url_abs":"https://arxiv.org/abs/2305.14336v5","url_pdf":"https://arxiv.org/pdf/2305.14336v5.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"schema-driven-information-extraction-from","repo_url":"https://github.com/bflashcp3f/schema-to-json","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"attribute-extraction","task_name":"Attribute Extraction"},{"task_slug":"instruction-following","task_name":"Instruction Following"},{"task_slug":"table-extraction","task_name":"Table Extraction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/attribute-extraction-on-swde","task":"Attribute Extraction","dataset":"SWDE","model":"InstrucTE (zero-shot)","rank_in_archive_order":1,"of":2,"metrics":{"Avg F1":"95.7"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2305.14336","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}