@inproceedings{kim-etal-2023-chatgpt,
title = "Can {C}hat{GPT} Understand Causal Language in Science Claims?",
author = "Kim, Yuheun and
Guo, Lu and
Yu, Bei and
Li, Yingya",
editor = "Barnes, Jeremy and
De Clercq, Orph{\'e}e and
Klinger, Roman",
booktitle = "Proceedings of the 13th Workshop on Computational Approaches to Subjectivity, Sentiment, {\&} Social Media Analysis",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.wassa-1.33/",
doi = "10.18653/v1/2023.wassa-1.33",
pages = "379--389",
abstract = "This study evaluated ChatGPT`s ability to understand causal language in science papers and news by testing its accuracy in a task of labeling the strength of a claim as causal, conditional causal, correlational, or no relationship. The results show that ChatGPT is still behind the existing fine-tuned BERT models by a large margin. ChatGPT also had difficulty understanding conditional causal claims mitigated by hedges. However, its weakness may be utilized to improve the clarity of human annotation guideline. Chain-of-Thoughts were faithful and helpful for improving prompt performance, but finding the optimal prompt is difficult with inconsistent results and the lack of effective method to establish cause-effect between prompts and outcomes, suggesting caution when generalizing prompt engineering results across tasks or models."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kim-etal-2023-chatgpt">
<titleInfo>
<title>Can ChatGPT Understand Causal Language in Science Claims?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuheun</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bei</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yingya</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 13th Workshop on Computational Approaches to Subjectivity, Sentiment, & Social Media Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jeremy</namePart>
<namePart type="family">Barnes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Orphée</namePart>
<namePart type="family">De Clercq</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roman</namePart>
<namePart type="family">Klinger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This study evaluated ChatGPT‘s ability to understand causal language in science papers and news by testing its accuracy in a task of labeling the strength of a claim as causal, conditional causal, correlational, or no relationship. The results show that ChatGPT is still behind the existing fine-tuned BERT models by a large margin. ChatGPT also had difficulty understanding conditional causal claims mitigated by hedges. However, its weakness may be utilized to improve the clarity of human annotation guideline. Chain-of-Thoughts were faithful and helpful for improving prompt performance, but finding the optimal prompt is difficult with inconsistent results and the lack of effective method to establish cause-effect between prompts and outcomes, suggesting caution when generalizing prompt engineering results across tasks or models.</abstract>
<identifier type="citekey">kim-etal-2023-chatgpt</identifier>
<identifier type="doi">10.18653/v1/2023.wassa-1.33</identifier>
<location>
<url>https://aclanthology.org/2023.wassa-1.33/</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>379</start>
<end>389</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Can ChatGPT Understand Causal Language in Science Claims?
%A Kim, Yuheun
%A Guo, Lu
%A Yu, Bei
%A Li, Yingya
%Y Barnes, Jeremy
%Y De Clercq, Orphée
%Y Klinger, Roman
%S Proceedings of the 13th Workshop on Computational Approaches to Subjectivity, Sentiment, & Social Media Analysis
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F kim-etal-2023-chatgpt
%X This study evaluated ChatGPT‘s ability to understand causal language in science papers and news by testing its accuracy in a task of labeling the strength of a claim as causal, conditional causal, correlational, or no relationship. The results show that ChatGPT is still behind the existing fine-tuned BERT models by a large margin. ChatGPT also had difficulty understanding conditional causal claims mitigated by hedges. However, its weakness may be utilized to improve the clarity of human annotation guideline. Chain-of-Thoughts were faithful and helpful for improving prompt performance, but finding the optimal prompt is difficult with inconsistent results and the lack of effective method to establish cause-effect between prompts and outcomes, suggesting caution when generalizing prompt engineering results across tasks or models.
%R 10.18653/v1/2023.wassa-1.33
%U https://aclanthology.org/2023.wassa-1.33/
%U https://doi.org/10.18653/v1/2023.wassa-1.33
%P 379-389
Markdown (Informal)
[Can ChatGPT Understand Causal Language in Science Claims?](https://aclanthology.org/2023.wassa-1.33/) (Kim et al., WASSA 2023)
ACL
- Yuheun Kim, Lu Guo, Bei Yu, and Yingya Li. 2023. Can ChatGPT Understand Causal Language in Science Claims?. In Proceedings of the 13th Workshop on Computational Approaches to Subjectivity, Sentiment, & Social Media Analysis, pages 379–389, Toronto, Canada. Association for Computational Linguistics.