Papers › Statements: Universal Information Extraction from Tables with Large Language Models...

Statements: Universal Information Extraction from Tables with Large Language Models for ESG KPIs

27 Jun 2024arXiv:2406.19102archive 2025-07-28

Lokesh Mishra, Sohayl Dhibi, Yusik Kim, Cesar Berrospi Ramis, Shubham Gupta, Michele Dolfi, Peter Staar

Environment, Social, and Governance (ESG) KPIs assess an organization's performance on issues such as climate change, greenhouse gas emissions, water consumption, waste management, human rights, diversity, and policies. ESG reports convey this valuable quantitative information through tables. Unfortunately, extracting this information is difficult due to high variability in the table structure as well as content. We propose Statements, a novel domain agnostic data structure for extracting quantitative facts and related information. We propose translating tables to statements as a new supervised deep-learning universal information extraction task. We introduce SemTabNet - a dataset of over 100K annotated tables. Investigating a family of T5-based Statement Extraction Models, our best model generates statements which are 82% similar to the ground-truth (compared to baseline of 21%). We demonstrate the advantages of statements by applying our model to over 2700 tables from ESG reports. The homogeneous nature of statements permits exploratory data analysis on expansive information found in large collections of ESG reports.

PaperPDFCode

Code

ds4sd/semtabnet officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Information ExtractionNamed Entity RecognitionOpen Information ExtractionRelationship Extraction (Distant Supervised)Table annotation

Datasets

Introduced by this paper, per the archive.

SemTabNet

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Information Extraction SemTabNet T5 average Tree Similarity Score 81.76 #1 of 1 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections