Extracting AI agent-accessible data from biodiversity literature with corpus
Current Biology · 2026
DOI: 10.1016/j.cub.2026.08.019 ↗Kurz gefasst
Fachartikel in der Zeitschrift Current Biology, 2026. Verfasst von Samuel H Church und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biology, New York University, New York, NY 10003, USA. Electronic address: samuel.church@nyu.edu. Hauptthemen laut MEDLINE: Biodiversity, Artificial Intelligence, Information Storage and Retrieval. Die Arbeit nennt 9 Literaturangaben.
Abstract (Originalsprache)
Much of our shared knowledge about biodiversity, including data on species' traits, relationships, and occurrences, is stored in the published literature. This body of knowledge can span multiple centuries, languages, and publication formats, making it challenging to collect, compare, and synthesize data across entire clades. New artificial intelligence (AI) tools, including large language models (LLMs) in particular, are well suited to integrate and summarize large bodies of text and figures. However, the biodiversity literature is too large and multi-layered to be reliably interrogated by simply placing publications into an LLM context window. For the typical tasks of biodiversity scientists (e.g., assembling descriptive characters, reconstructing nomenclatural history), we need structured, provenance-aware, and deterministic data retrieval. Here we present corpus: a tool for converting biodiversity literature PDFs for a clade of organisms into a searchable knowledge base (a 'corpuscle') of text, figures, and references. Users connect an LLM client via corpus' Model Context Protocol (MCP) server, to interact directly with the processed literature through predefined search tools. corpus addresses critical gaps in LLM applications for biology by transforming the literature into an explicit retrieval layer, rather than relying on hidden training data or probabilistic recollection.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Biology, New York University, New York, NY 10003, USA. Electronic address: samuel.church@nyu.edu.
- Department of Marine Biology and Biotechnology, University of Gdańsk, 81-378 Gdynia, Poland.
- Department of Ecology and Evolutionary Biology and Center for Tropical Research, University of California, Los Angeles, CA 90095, USA.
- Department of Ecology and Evolutionary Biology and Quantitative Biology Institute, Yale University, New Haven, CT 06511, USA.
Zitieren
APA
Church, S. H., Mańko, M. K., Zapata, F., & Dunn, C. W. (2026). Extracting AI agent-accessible data from biodiversity literature with corpus. Current Biology. https://doi.org/10.1016/j.cub.2026.08.019
Vancouver
Church SH, Mańko MK, Zapata F, Dunn CW. Extracting AI agent-accessible data from biodiversity literature with corpus. Current Biology. 2026. doi:10.1016/j.cub.2026.08.019
BibTeX
@article{Church2026,
author = {Church, Samuel H and Mańko, Maciej K and Zapata, Felipe and Dunn, Casey W},
title = {Extracting AI agent-accessible data from biodiversity literature with corpus},
journal = {Current Biology},
year = {2026},
doi = {10.1016/j.cub.2026.08.019}
}
EUVIMED