@inproceedings{wang-etal-2024-rethinking,
title = "Rethinking {STS} and {NLI} in Large Language Models",
author = "Wang, Yuxia and
Wang, Minghan and
Nakov, Preslav",
editor = "Graham, Yvette and
Purver, Matthew",
booktitle = "Findings of the Association for Computational Linguistics: EACL 2024",
month = mar,
year = "2024",
address = "St. Julian{'}s, Malta",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-eacl.65",
pages = "965--982",
abstract = "Recent years, have seen the rise of large language models (LLMs), where practitioners use task-specific prompts; this was shown to be effective for a variety of tasks. However, when applied to semantic textual similarity (STS) and natural language inference (NLI), the effectiveness of LLMs turns out to be limited by low-resource domain accuracy, model overconfidence, and difficulty to capture the disagreements between human judgements. With this in mind, here we try to rethink STS and NLI in the era of LLMs. We first evaluate the performance of STS and NLI in the clinical/biomedical domain, and then we assess LLMs{'} predictive confidence and their capability of capturing collective human opinions. We find that these old problems are still to be properly addressed in the era of LLMs.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2024-rethinking">
<titleInfo>
<title>Rethinking STS and NLI in Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuxia</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minghan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yvette</namePart>
<namePart type="family">Graham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="family">Purver</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">St. Julian’s, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent years, have seen the rise of large language models (LLMs), where practitioners use task-specific prompts; this was shown to be effective for a variety of tasks. However, when applied to semantic textual similarity (STS) and natural language inference (NLI), the effectiveness of LLMs turns out to be limited by low-resource domain accuracy, model overconfidence, and difficulty to capture the disagreements between human judgements. With this in mind, here we try to rethink STS and NLI in the era of LLMs. We first evaluate the performance of STS and NLI in the clinical/biomedical domain, and then we assess LLMs’ predictive confidence and their capability of capturing collective human opinions. We find that these old problems are still to be properly addressed in the era of LLMs.</abstract>
<identifier type="citekey">wang-etal-2024-rethinking</identifier>
<location>
<url>https://aclanthology.org/2024.findings-eacl.65</url>
</location>
<part>
<date>2024-03</date>
<extent unit="page">
<start>965</start>
<end>982</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Rethinking STS and NLI in Large Language Models
%A Wang, Yuxia
%A Wang, Minghan
%A Nakov, Preslav
%Y Graham, Yvette
%Y Purver, Matthew
%S Findings of the Association for Computational Linguistics: EACL 2024
%D 2024
%8 March
%I Association for Computational Linguistics
%C St. Julian’s, Malta
%F wang-etal-2024-rethinking
%X Recent years, have seen the rise of large language models (LLMs), where practitioners use task-specific prompts; this was shown to be effective for a variety of tasks. However, when applied to semantic textual similarity (STS) and natural language inference (NLI), the effectiveness of LLMs turns out to be limited by low-resource domain accuracy, model overconfidence, and difficulty to capture the disagreements between human judgements. With this in mind, here we try to rethink STS and NLI in the era of LLMs. We first evaluate the performance of STS and NLI in the clinical/biomedical domain, and then we assess LLMs’ predictive confidence and their capability of capturing collective human opinions. We find that these old problems are still to be properly addressed in the era of LLMs.
%U https://aclanthology.org/2024.findings-eacl.65
%P 965-982
Markdown (Informal)
[Rethinking STS and NLI in Large Language Models](https://aclanthology.org/2024.findings-eacl.65) (Wang et al., Findings 2024)
ACL
- Yuxia Wang, Minghan Wang, and Preslav Nakov. 2024. Rethinking STS and NLI in Large Language Models. In Findings of the Association for Computational Linguistics: EACL 2024, pages 965–982, St. Julian’s, Malta. Association for Computational Linguistics.