Environmental Studies and Forestry

Testing the reliability of an AI-based large language model to extract ecological information from the scientific literature

A. V. Gougherty and H. L. Clipp

This groundbreaking research by Andrew V. Gougherty and Hannah L. Clipp reveals how a large language model (LLM) can extract ecological data from scientific literature over 50 times faster than human reviewers, while achieving remarkable accuracy. Discover its potential for creating extensive ecological databases, but also the essential need for quality assurance to ensure data integrity!

00:00

Playback language: English

Index

Abstract

This study assesses the speed and accuracy of a large language model (LLM) in extracting ecological data from scientific literature compared to a human reviewer. The LLM extracted data over 50 times faster, achieving >90% accuracy for discrete and categorical data but showing lower accuracy for quantitative data. The findings highlight the LLM's potential for creating large ecological databases but emphasize the need for quality assurance to maintain data integrity.

Publisher

npj Biodiversity

Published On

May 16, 2024

Authors

Andrew V. Gougherty, Hannah L. Clipp

Related Publications

Explore these studies to deepen your understanding of the subject.

Medicine and Health

A scoping review of large language model based approaches for information extraction from radiology reports

D. Reichenpfader, H. Müller, et al.

Business

Understanding continuance intention of artificial intelligence (AI)-enabled mobile banking applications: an extension of AI characteristics to an expectation confirmation model

J. Lee, Y. Tang, et al.

Social Work

Evaluating the effectiveness of the Kidogo model in empowering women and strengthening their capacities to engage in paid labor opportunities through the provision of quality childcare: a study protocol for an exploratory study in Nakuru County, Kenya

K. Okelo, M. Nampijja, et al.

Linguistics and Languages

The potential of emotive language to influence the understanding of textual information in media coverage

A. Absattar, M. Mambetova, et al.

Listen, Learn & Level Up

Over 10,000 hours of research content in 25+ fields, available in 12+ languages.

No more digging through PDFs, just hit play and absorb the world's latest research in your language, on your time.

listen to research audio papers with researchbunny