@inproceedings{dsouza-etal-2025-mining,
title = "Mining for Species, Locations, Habitats, and Ecosystems from Scientific Papers in Invasion Biology: {A} Large-Scale Exploratory Study with Large Language Models",
author = {D{'}Souza, Jennifer and
Laubach, Zachary and
Mustafa, Tarek Al and
Zarrie{\ss}, Sina and
Fr{\"u}hst{\"u}ckl, Robert and
Illari, Phyllis},
editor = "Basile, Valerio and
Bosco, Cristina and
Grasso, Francesca and
Ibrohim, Muhammad Okky and
Skeppstedt, Maria and
Stede, Manfred",
booktitle = "Proceedings of the 1st Workshop on Ecology, Environment, and Natural Language Processing (NLP4Ecology2025)",
month = mar,
year = "2025",
address = "Tallinn, Estonia",
publisher = "University of Tartu Library",
url = "https://aclanthology.org/2025.nlp4ecology-1.6/",
pages = "16--23",
ISBN = "978-9908-53-114-4",
abstract = "This study explores the use of large language models (LLMs), specifically GPT-4o, to extract key ecological entities{---}species, locations, habitats, and ecosystems{---}from invasion biology literature. This information is critical for understanding species spread, predicting future invasions, and informing conservation efforts. Without domain-specific fine-tuning, we assess the potential and limitations of GPT-4o, out-of-the-box, for this task, highlighting the role of LLMs in advancing automated knowledge extraction for ecological research and management."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dsouza-etal-2025-mining">
<titleInfo>
<title>Mining for Species, Locations, Habitats, and Ecosystems from Scientific Papers in Invasion Biology: A Large-Scale Exploratory Study with Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jennifer</namePart>
<namePart type="family">D’Souza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zachary</namePart>
<namePart type="family">Laubach</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tarek</namePart>
<namePart type="given">Al</namePart>
<namePart type="family">Mustafa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sina</namePart>
<namePart type="family">Zarrieß</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robert</namePart>
<namePart type="family">Frühstückl</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Phyllis</namePart>
<namePart type="family">Illari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Workshop on Ecology, Environment, and Natural Language Processing (NLP4Ecology2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Valerio</namePart>
<namePart type="family">Basile</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cristina</namePart>
<namePart type="family">Bosco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francesca</namePart>
<namePart type="family">Grasso</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="given">Okky</namePart>
<namePart type="family">Ibrohim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Skeppstedt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manfred</namePart>
<namePart type="family">Stede</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>University of Tartu Library</publisher>
<place>
<placeTerm type="text">Tallinn, Estonia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">978-9908-53-114-4</identifier>
</relatedItem>
<abstract>This study explores the use of large language models (LLMs), specifically GPT-4o, to extract key ecological entities—species, locations, habitats, and ecosystems—from invasion biology literature. This information is critical for understanding species spread, predicting future invasions, and informing conservation efforts. Without domain-specific fine-tuning, we assess the potential and limitations of GPT-4o, out-of-the-box, for this task, highlighting the role of LLMs in advancing automated knowledge extraction for ecological research and management.</abstract>
<identifier type="citekey">dsouza-etal-2025-mining</identifier>
<location>
<url>https://aclanthology.org/2025.nlp4ecology-1.6/</url>
</location>
<part>
<date>2025-03</date>
<extent unit="page">
<start>16</start>
<end>23</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Mining for Species, Locations, Habitats, and Ecosystems from Scientific Papers in Invasion Biology: A Large-Scale Exploratory Study with Large Language Models
%A D’Souza, Jennifer
%A Laubach, Zachary
%A Mustafa, Tarek Al
%A Zarrieß, Sina
%A Frühstückl, Robert
%A Illari, Phyllis
%Y Basile, Valerio
%Y Bosco, Cristina
%Y Grasso, Francesca
%Y Ibrohim, Muhammad Okky
%Y Skeppstedt, Maria
%Y Stede, Manfred
%S Proceedings of the 1st Workshop on Ecology, Environment, and Natural Language Processing (NLP4Ecology2025)
%D 2025
%8 March
%I University of Tartu Library
%C Tallinn, Estonia
%@ 978-9908-53-114-4
%F dsouza-etal-2025-mining
%X This study explores the use of large language models (LLMs), specifically GPT-4o, to extract key ecological entities—species, locations, habitats, and ecosystems—from invasion biology literature. This information is critical for understanding species spread, predicting future invasions, and informing conservation efforts. Without domain-specific fine-tuning, we assess the potential and limitations of GPT-4o, out-of-the-box, for this task, highlighting the role of LLMs in advancing automated knowledge extraction for ecological research and management.
%U https://aclanthology.org/2025.nlp4ecology-1.6/
%P 16-23
Markdown (Informal)
[Mining for Species, Locations, Habitats, and Ecosystems from Scientific Papers in Invasion Biology: A Large-Scale Exploratory Study with Large Language Models](https://aclanthology.org/2025.nlp4ecology-1.6/) (D’Souza et al., NLP4Ecology 2025)
ACL
- Jennifer D’Souza, Zachary Laubach, Tarek Al Mustafa, Sina Zarrieß, Robert Frühstückl, and Phyllis Illari. 2025. Mining for Species, Locations, Habitats, and Ecosystems from Scientific Papers in Invasion Biology: A Large-Scale Exploratory Study with Large Language Models. In Proceedings of the 1st Workshop on Ecology, Environment, and Natural Language Processing (NLP4Ecology2025), pages 16–23, Tallinn, Estonia. University of Tartu Library.