{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,15]],"date-time":"2026-11-15T11:34:45Z","timestamp":1794742485827,"version":"4.9.1"},"reference-count":78,"publisher":"Wiley","issue":"11","license":[{"start":{"date-parts":[[2026,10,27]],"date-time":"2026-10-27T00:00:00Z","timestamp":1793059200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,10,27]],"date-time":"2026-10-27T00:00:00Z","timestamp":1793059200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/501100001711","name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","doi-asserted-by":"publisher","award":["310030_197410"],"award-info":[{"award-number":["310030_197410"]}],"id":[{"id":"10.13039\/501100001711","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006447","name":"Universit\u00e4t Z\u00fcrich","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100006447","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Ecology and Evolution"],"published-print":{"date-parts":[[2026,11]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>The contemporary ecological crisis calls for integration and synthesis of vast amounts of mostly scattered and often hard\u2010to\u2010extract ecological information that is dispersed across hundreds of thousands of scientific papers. Recent advancements in natural language processing (NLP) and the emergence of large language models (LLMs) offer a novel and promising approach to this persistent challenge. Here, we present a replicable and adaptable workflow that automates the extraction of a broad range of biological interactions among species from scientific literature using LLMs. We provide a demonstration of this workflow by performing a large\u2010scale data extraction directly from a corpus of 83,910 scientific articles using OpenAI GPT\u20104o. Our approach successfully extracted a network of 144,402 interactions between 36,471 taxa. Performance analysis shows that the model exhibits a precision of 89.5% with a recall of 70.0%, demonstrating that a general\u2010purpose LLM can perform complex ecological information extraction at scale for analysis and synthesis. Results depend on quality filtering choices and inherit biases present in the underlying literature, emphasizing the need for validation and quality control. Standardized outputs can be browsed, queried, or joined with existing interaction repositories and taxonomic backbones, facilitating downstream reuse and interoperability. Our case study shows that LLMs are capable of carrying out complex extraction tasks on key ecological data on a very large scale, paving the way for a multitude of potential applications in ecology and beyond.<\/jats:p>","DOI":"10.1002\/ece3.74626","type":"journal-article","created":{"date-parts":[[2026,10,28]],"date-time":"2026-10-28T01:27:54Z","timestamp":1793150874000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A Scalable Workflow for Extracting Species Interactions From Ecological Literature Using Large Language Models"],"prefix":"10.1002","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3323-4167","authenticated-orcid":false,"given":"Fran\u00e7ois","family":"Keck","sequence":"first","affiliation":[{"name":"Department of Evolutionary Biology and Environmental Studies University of Zurich  Z\u00fcrich Switzerland"},{"name":"Department of Aquatic Ecology Eawag, Swiss Federal Institute of Aquatic Science and Technology  D\u00fcbendorf Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Henry","family":"Broadbent","sequence":"additional","affiliation":[{"name":"Department of Evolutionary Biology and Environmental Studies University of Zurich  Z\u00fcrich Switzerland"},{"name":"Department of Aquatic Ecology Eawag, Swiss Federal Institute of Aquatic Science and Technology  D\u00fcbendorf Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Florian","family":"Altermatt","sequence":"additional","affiliation":[{"name":"Department of Evolutionary Biology and Environmental Studies University of Zurich  Z\u00fcrich Switzerland"},{"name":"Department of Aquatic Ecology Eawag, Swiss Federal Institute of Aquatic Science and Technology  D\u00fcbendorf Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,10,27]]},"reference":[{"key":"e_1_2_10_2_1","doi-asserted-by":"publisher","DOI":"10.3897\/BDJ.10.e89481"},{"key":"e_1_2_10_3_1","doi-asserted-by":"crossref","unstructured":"Alizadeh M. M.Kubli Z.Samei et\u00a0al.2024.\u201cOpen\u2010Source LLMs for Text Annotation: A Practical Guide for Model Setting and Fine\u2010Tuning.\u201darXiv: 2307.02179.https:\/\/doi.org\/10.48550\/arXiv.2307.02179.","DOI":"10.1007\/s42001-024-00345-9"},{"key":"e_1_2_10_4_1","unstructured":"Amatriain X.2024.\u201cPrompt Design and Engineering: Introduction and Advanced Methods.\u201darXiv: 2401.14423; Version 3).https:\/\/doi.org\/10.48550\/arXiv.2401.14423."},{"key":"e_1_2_10_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.tree.2024.04.007"},{"key":"e_1_2_10_6_1","unstructured":"Brown T. B. B.Mann N.Ryder et\u00a0al.2020.\u201cLanguage Models Are Few\u2010Shot Learners.\u201darXiv: 2005.14165.https:\/\/doi.org\/10.48550\/arXiv.2005.14165."},{"key":"e_1_2_10_7_1","doi-asserted-by":"publisher","DOI":"10.3732\/ajb.1000391"},{"key":"e_1_2_10_8_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1821843116"},{"key":"e_1_2_10_9_1","doi-asserted-by":"publisher","DOI":"10.1002\/ecs2.2645"},{"key":"e_1_2_10_10_1","doi-asserted-by":"publisher","DOI":"10.1111\/2041\u2010210X.14396"},{"key":"e_1_2_10_11_1","unstructured":"Carammia M. S. M.Iacus andG.Porro.2024.\u201cRethinking Scale: The Efficacy of Fine\u2010Tuned Open\u2010Source LLMs in Large\u2010Scale Reproducible Social Science Research.\u201darXiv: 2411.00890.https:\/\/doi.org\/10.48550\/arXiv.2411.00890."},{"key":"e_1_2_10_12_1","volume-title":"Silent Spring","author":"Carson R.","year":"1962"},{"key":"e_1_2_10_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecoinf.2024.102742"},{"key":"e_1_2_10_14_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1365\u20102656.2011.01883.x"},{"key":"e_1_2_10_15_1","unstructured":"Chen L. andG.Varoquaux.2024.\u201cWhat Is the Role of Small Models in the LLM Era: A Survey.\u201darXiv: 2409.06857.https:\/\/doi.org\/10.48550\/arXiv.2409.06857."},{"key":"e_1_2_10_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecoinf.2023.102312"},{"key":"e_1_2_10_17_1","doi-asserted-by":"publisher","DOI":"10.1111\/2041\u2010210X.14325"},{"key":"e_1_2_10_18_1","doi-asserted-by":"publisher","DOI":"10.1111\/ecog.06068"},{"key":"e_1_2_10_19_1","doi-asserted-by":"publisher","DOI":"10.1111\/brv.12433"},{"key":"e_1_2_10_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecoinf.2026.103699"},{"key":"e_1_2_10_21_1","first-page":"16","volume-title":"Proceedings of the 1st Workshop on Ecology, Environment, and Natural Language Processing (NLP4Ecology2025)","author":"D'Souza J.","year":"2025"},{"key":"e_1_2_10_22_1","first-page":"1","volume-title":"Animal Ecology","author":"Elton C. S.","year":"1927"},{"key":"e_1_2_10_23_1","doi-asserted-by":"publisher","DOI":"10.1098\/rspb.2024.0423"},{"key":"e_1_2_10_24_1","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkr1178"},{"key":"e_1_2_10_25_1","doi-asserted-by":"publisher","DOI":"10.1111\/geb.13497"},{"key":"e_1_2_10_26_1","doi-asserted-by":"publisher","DOI":"10.1111\/2041\u2010210X.70184"},{"key":"e_1_2_10_27_1","doi-asserted-by":"publisher","DOI":"10.1038\/s44185\u2010024\u201000043\u20109"},{"key":"e_1_2_10_28_1","doi-asserted-by":"publisher","DOI":"10.1146\/annurev\u2010ecolsys\u2010012220\u2010120819"},{"key":"e_1_2_10_29_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1461\u20100248.2008.01269.x"},{"key":"e_1_2_10_30_1","doi-asserted-by":"publisher","DOI":"10.1890\/060108"},{"key":"e_1_2_10_31_1","doi-asserted-by":"publisher","DOI":"10.1146\/annurev\u2010ecolsys\u2010112414\u2010054400"},{"key":"e_1_2_10_32_1","doi-asserted-by":"crossref","unstructured":"Humboldt A. v. A. andA.Bonpland.1805.\u201cEssai sur la G\u00e9ographie des Plantes: Accompagn\u00e9 d'un Tableau Physique des R\u00e9gions \u00c9quinoxiales Fond\u00e9 sur des Mesures Ex\u00e9cut\u00e9es Depuis le Dixi\u00e8me Degr\u00e9 de Latitude Bor\u00e9ale Jusqu'au Dixi\u00e8me Degr\u00e9 de Latitude Australe Pendant les Ann\u00e9es 1799 1800 1801 1802 et 1803 ([Reprod.]).\u201dParis: Levrault Schoell et Cie.https:\/\/gallica.bnf.fr\/ark:\/12148\/bpt6k977938.","DOI":"10.5962\/bhl.title.9309"},{"key":"e_1_2_10_33_1","doi-asserted-by":"publisher","DOI":"10.1038\/d41586\u2010022\u201003479\u2010w"},{"key":"e_1_2_10_34_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0323563"},{"key":"e_1_2_10_35_1","unstructured":"Kaplan J. S.McCandlish T.Henighan et\u00a0al.2020.\u201cScaling Laws for Neural Language Models.\u201darXiv: 2001.08361.https:\/\/doi.org\/10.48550\/arXiv.2001.08361."},{"key":"e_1_2_10_36_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.lindif.2023.102274"},{"key":"e_1_2_10_37_1","doi-asserted-by":"publisher","DOI":"10.1111\/2041\u2010210X.13778"},{"key":"e_1_2_10_38_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature22898"},{"key":"e_1_2_10_39_1","doi-asserted-by":"publisher","DOI":"10.1111\/geb.13138"},{"key":"e_1_2_10_40_1","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms10245"},{"key":"e_1_2_10_41_1","doi-asserted-by":"publisher","DOI":"10.1111\/ecog.04532"},{"key":"e_1_2_10_42_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecoinf.2024.102545"},{"key":"e_1_2_10_43_1","doi-asserted-by":"publisher","DOI":"10.3897\/BDJ.7.e28737"},{"key":"e_1_2_10_44_1","doi-asserted-by":"crossref","unstructured":"Nayab S. G.Rossolini M.Simoni et\u00a0al.2025.\u201cConcise Thoughts: Impact of Output Length on LLM Reasoning and Cost.\u201darXiv: 2407.19825.https:\/\/doi.org\/10.48550\/arXiv.2407.19825.","DOI":"10.2139\/ssrn.5293076"},{"key":"e_1_2_10_45_1","doi-asserted-by":"publisher","DOI":"10.1111\/2041\u2010210X.12602"},{"key":"e_1_2_10_46_1","doi-asserted-by":"crossref","DOI":"10.31235\/osf.io\/x58kn","volume-title":"ChatGPT for Text Annotation? Mind the Hype!","author":"Ollion E.","year":"2023"},{"key":"e_1_2_10_47_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256\u2010023\u201000783\u20106"},{"key":"e_1_2_10_48_1","unstructured":"OpenAI J.Achiam S.Adler et\u00a0al.2023.\u201cGPT\u20104 Technical Report.\u201darXiv: 2303.08774.https:\/\/doi.org\/10.48550\/arXiv.2303.08774."},{"key":"e_1_2_10_49_1","doi-asserted-by":"crossref","first-page":"27730","DOI":"10.52202\/068431-2011","article-title":"Training Language Models to Follow Instructions With Human Feedback","volume":"35","author":"Ouyang L.","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_10_50_1","doi-asserted-by":"publisher","DOI":"10.1086\/282400"},{"key":"e_1_2_10_51_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecoinf.2026.103813"},{"key":"e_1_2_10_52_1","doi-asserted-by":"publisher","DOI":"10.1890\/12\u20101075.1"},{"key":"e_1_2_10_53_1","doi-asserted-by":"publisher","DOI":"10.1111\/ele.12143"},{"key":"e_1_2_10_54_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecoinf.2014.08.005"},{"key":"e_1_2_10_55_1","doi-asserted-by":"publisher","DOI":"10.1111\/ecog.00976"},{"key":"e_1_2_10_56_1","doi-asserted-by":"publisher","DOI":"10.1111\/jbi.14127"},{"key":"e_1_2_10_57_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.tree.2020.08.015"},{"key":"e_1_2_10_58_1","unstructured":"Priem J. H.Piwowar andR.Orr.2022.\u201cOpenAlex: A Fully\u2010Open Index of Scholarly Works Authors Venues Institutions and Concepts.\u201darXiv: 2205.01833.https:\/\/doi.org\/10.48550\/arXiv.2205.01833."},{"key":"e_1_2_10_59_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41559\u2010024\u201002623\u20101"},{"key":"e_1_2_10_60_1","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1007\/978-3-642-28569-1_5","volume-title":"Multi\u2010Source, Multilingual Information Extraction and Summarization","author":"Rao D.","year":"2013"},{"key":"e_1_2_10_61_1","doi-asserted-by":"crossref","first-page":"271","DOI":"10.1002\/9781444324044.ch11","volume-title":"The Handbook of Computational Linguistics and Natural Language Processing","author":"Resnik P.","year":"2010"},{"key":"e_1_2_10_62_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.98.2.381"},{"key":"e_1_2_10_63_1","doi-asserted-by":"publisher","DOI":"10.1002\/eap.2608"},{"key":"e_1_2_10_64_1","doi-asserted-by":"publisher","DOI":"10.1111\/2041\u2010210X.14341"},{"key":"e_1_2_10_65_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.tree.2018.07.001"},{"key":"e_1_2_10_66_1","doi-asserted-by":"crossref","unstructured":"Sommers F. A.Kongthon andS.Kongyoung.2024.\u201cFine\u2010Tuning Large Language Models for Private Document Retrieval: A Tutorial.\u201dProceedings of the 2024 International Conference on Multimedia Retrieval ICMR \u02bb24 1319\u20131320.https:\/\/doi.org\/10.1145\/3652583.3658419.","DOI":"10.1145\/3652583.3658419"},{"key":"e_1_2_10_67_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.envsoft.2026.106865"},{"key":"e_1_2_10_68_1","doi-asserted-by":"publisher","DOI":"10.1111\/ele.12770"},{"key":"e_1_2_10_69_1","doi-asserted-by":"crossref","first-page":"225","DOI":"10.1016\/B978-0-12-420002-9.00004-4","volume-title":"Ecological Networks in an Agricultural World","author":"Tamaddoni\u2010Nezhad A.","year":"2013"},{"key":"e_1_2_10_70_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0089550"},{"key":"e_1_2_10_71_1","doi-asserted-by":"publisher","DOI":"10.5840\/philtopics201947111"},{"key":"e_1_2_10_72_1","first-page":"24","volume-title":"Proceedings of the 1st Workshop on Ecology, Environment, and Natural Language Processing (NLP4Ecology2025)","author":"Volkanovska E.","year":"2025"},{"key":"e_1_2_10_73_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467\u2010021\u201021034\u20105"},{"key":"e_1_2_10_74_1","unstructured":"Wei J. Y.Tay R.Bommasani et\u00a0al.2022.\u201cEmergent Abilities of Large Language Models.\u201darXiv: 2206.07682.https:\/\/doi.org\/10.48550\/arXiv.2206.07682."},{"key":"e_1_2_10_75_1","unstructured":"Wei J. X.Wang D.Schuurmans et\u00a0al.2023.\u201cChain\u2010of\u2010Thought Prompting Elicits Reasoning in Large Language Models.\u201darXiv: 2201.11903.https:\/\/doi.org\/10.48550\/arXiv.2201.11903."},{"key":"e_1_2_10_76_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1469\u2010185X.2012.00235.x"},{"key":"e_1_2_10_77_1","unstructured":"Yurtsev E.2024.\u201cEyurtsev\/kor [Python].\u201d Original Work Published 2023.https:\/\/github.com\/eyurtsev\/kor."},{"key":"e_1_2_10_78_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41746\u2010024\u201001239\u2010w"},{"key":"e_1_2_10_79_1","doi-asserted-by":"crossref","unstructured":"Zou H.\u2010X. X.Yang T. H.Hajamaideen et\u00a0al.2026.\u201cLarge Language Models Unlock the Ecology of Species Interactions.\u201dbioRxiv: The Preprint Server for Biology: 2026.02.06.704115.https:\/\/doi.org\/10.64898\/2026.02.06.704115.","DOI":"10.64898\/2026.02.06.704115"}],"container-title":["Ecology and Evolution"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/ece3.74626","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/ece3.74626","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/ece3.74626","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,28]],"date-time":"2026-10-28T01:27:59Z","timestamp":1793150879000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/ece3.74626"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,27]]},"references-count":78,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2026,11]]}},"alternative-id":["10.1002\/ece3.74626"],"URL":"https:\/\/doi.org\/10.1002\/ece3.74626","archive":["Portico"],"relation":{},"ISSN":["2045-7758","2045-7758"],"issn-type":[{"value":"2045-7758","type":"print"},{"value":"2045-7758","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,27]]},"assertion":[{"value":"2026-05-28","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-09-29","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e74626"}}