@inproceedings{koneru-etal-2024-large-language,
title = "Can Large Language Models Discern Evidence for Scientific Hypotheses? Case Studies in the Social Sciences",
author = "Koneru, Sai and
Wu, Jian and
Rajtmajer, Sarah",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.248",
pages = "2787--2797",
abstract = "Hypothesis formulation and testing are central to empirical research. A strong hypothesis is a best guess based on existing evidence and informed by a comprehensive view of relevant literature. However, with exponential increase in the number of scientific articles published annually, manual aggregation and synthesis of evidence related to a given hypothesis is a challenge. Our work explores the ability of current large language models (LLMs) to discern evidence in support or refute of specific hypotheses based on the text of scientific abstracts. We share a novel dataset for the task of scientific hypothesis evidencing using community-driven annotations of studies in the social sciences. We compare the performance of LLMs to several state of the art methods and highlight opportunities for future research in this area. Our dataset is shared with the research community: https://github.com/Sai90000/ScientificHypothesisEvidencing.git",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="koneru-etal-2024-large-language">
<titleInfo>
<title>Can Large Language Models Discern Evidence for Scientific Hypotheses? Case Studies in the Social Sciences</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sai</namePart>
<namePart type="family">Koneru</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jian</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sarah</namePart>
<namePart type="family">Rajtmajer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Hypothesis formulation and testing are central to empirical research. A strong hypothesis is a best guess based on existing evidence and informed by a comprehensive view of relevant literature. However, with exponential increase in the number of scientific articles published annually, manual aggregation and synthesis of evidence related to a given hypothesis is a challenge. Our work explores the ability of current large language models (LLMs) to discern evidence in support or refute of specific hypotheses based on the text of scientific abstracts. We share a novel dataset for the task of scientific hypothesis evidencing using community-driven annotations of studies in the social sciences. We compare the performance of LLMs to several state of the art methods and highlight opportunities for future research in this area. Our dataset is shared with the research community: https://github.com/Sai90000/ScientificHypothesisEvidencing.git</abstract>
<identifier type="citekey">koneru-etal-2024-large-language</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.248</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>2787</start>
<end>2797</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Can Large Language Models Discern Evidence for Scientific Hypotheses? Case Studies in the Social Sciences
%A Koneru, Sai
%A Wu, Jian
%A Rajtmajer, Sarah
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F koneru-etal-2024-large-language
%X Hypothesis formulation and testing are central to empirical research. A strong hypothesis is a best guess based on existing evidence and informed by a comprehensive view of relevant literature. However, with exponential increase in the number of scientific articles published annually, manual aggregation and synthesis of evidence related to a given hypothesis is a challenge. Our work explores the ability of current large language models (LLMs) to discern evidence in support or refute of specific hypotheses based on the text of scientific abstracts. We share a novel dataset for the task of scientific hypothesis evidencing using community-driven annotations of studies in the social sciences. We compare the performance of LLMs to several state of the art methods and highlight opportunities for future research in this area. Our dataset is shared with the research community: https://github.com/Sai90000/ScientificHypothesisEvidencing.git
%U https://aclanthology.org/2024.lrec-main.248
%P 2787-2797
Markdown (Informal)
[Can Large Language Models Discern Evidence for Scientific Hypotheses? Case Studies in the Social Sciences](https://aclanthology.org/2024.lrec-main.248) (Koneru et al., LREC-COLING 2024)
ACL