@inproceedings{alvarez-etal-2024-zero,
title = "Zero-shot Scientific Claim Verification Using {LLM}s and Citation Text",
author = "Alvarez, Carlos and
Bennett, Maxwell and
Wang, Lucy",
editor = "Ghosal, Tirthankar and
Singh, Amanpreet and
Waard, Anita and
Mayr, Philipp and
Naik, Aakanksha and
Weller, Orion and
Lee, Yoonjoo and
Shen, Shannon and
Qin, Yanxia",
booktitle = "Proceedings of the Fourth Workshop on Scholarly Document Processing (SDP 2024)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.sdp-1.25",
pages = "269--276",
abstract = "Due to rapidly changing and advancing science, it is important to check the veracity of scientific claims and whether they are supported by research evidence. Previous versions of this task depended on supervised training, where labeled datasets were constructed through manual claim writing and evidence identification, sometimes coupled with mining citation relationships in papers. In this work, we investigate whether zero-shot scientific claim verification could be enabled using large language models (LLMs) and distant supervision examples taken directly from citation texts. We derive an in-context learning (ICL) dataset, SCitance, consisting of citation sentences ({``}citances{''}), LLM-generated negations, evidence documents, and veracity labels, and find that prompting GPT-4 with ICL examples from this dataset yields comparable performance (within 1 point F1) to previous finetuned models trained on manually curated claim-evidence pairs. Our results suggest that prompting LLMs with citance-evidence pairs directly poses a viable alternative to finetuning scientific claim verification models with manually-curated data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alvarez-etal-2024-zero">
<titleInfo>
<title>Zero-shot Scientific Claim Verification Using LLMs and Citation Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Carlos</namePart>
<namePart type="family">Alvarez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maxwell</namePart>
<namePart type="family">Bennett</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucy</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth Workshop on Scholarly Document Processing (SDP 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tirthankar</namePart>
<namePart type="family">Ghosal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amanpreet</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anita</namePart>
<namePart type="family">Waard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philipp</namePart>
<namePart type="family">Mayr</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aakanksha</namePart>
<namePart type="family">Naik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Orion</namePart>
<namePart type="family">Weller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yoonjoo</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shannon</namePart>
<namePart type="family">Shen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yanxia</namePart>
<namePart type="family">Qin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Due to rapidly changing and advancing science, it is important to check the veracity of scientific claims and whether they are supported by research evidence. Previous versions of this task depended on supervised training, where labeled datasets were constructed through manual claim writing and evidence identification, sometimes coupled with mining citation relationships in papers. In this work, we investigate whether zero-shot scientific claim verification could be enabled using large language models (LLMs) and distant supervision examples taken directly from citation texts. We derive an in-context learning (ICL) dataset, SCitance, consisting of citation sentences (“citances”), LLM-generated negations, evidence documents, and veracity labels, and find that prompting GPT-4 with ICL examples from this dataset yields comparable performance (within 1 point F1) to previous finetuned models trained on manually curated claim-evidence pairs. Our results suggest that prompting LLMs with citance-evidence pairs directly poses a viable alternative to finetuning scientific claim verification models with manually-curated data.</abstract>
<identifier type="citekey">alvarez-etal-2024-zero</identifier>
<location>
<url>https://aclanthology.org/2024.sdp-1.25</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>269</start>
<end>276</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Zero-shot Scientific Claim Verification Using LLMs and Citation Text
%A Alvarez, Carlos
%A Bennett, Maxwell
%A Wang, Lucy
%Y Ghosal, Tirthankar
%Y Singh, Amanpreet
%Y Waard, Anita
%Y Mayr, Philipp
%Y Naik, Aakanksha
%Y Weller, Orion
%Y Lee, Yoonjoo
%Y Shen, Shannon
%Y Qin, Yanxia
%S Proceedings of the Fourth Workshop on Scholarly Document Processing (SDP 2024)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F alvarez-etal-2024-zero
%X Due to rapidly changing and advancing science, it is important to check the veracity of scientific claims and whether they are supported by research evidence. Previous versions of this task depended on supervised training, where labeled datasets were constructed through manual claim writing and evidence identification, sometimes coupled with mining citation relationships in papers. In this work, we investigate whether zero-shot scientific claim verification could be enabled using large language models (LLMs) and distant supervision examples taken directly from citation texts. We derive an in-context learning (ICL) dataset, SCitance, consisting of citation sentences (“citances”), LLM-generated negations, evidence documents, and veracity labels, and find that prompting GPT-4 with ICL examples from this dataset yields comparable performance (within 1 point F1) to previous finetuned models trained on manually curated claim-evidence pairs. Our results suggest that prompting LLMs with citance-evidence pairs directly poses a viable alternative to finetuning scientific claim verification models with manually-curated data.
%U https://aclanthology.org/2024.sdp-1.25
%P 269-276
Markdown (Informal)
[Zero-shot Scientific Claim Verification Using LLMs and Citation Text](https://aclanthology.org/2024.sdp-1.25) (Alvarez et al., sdp-WS 2024)
ACL