@inproceedings{hayashi-2024-reassessing,
title = "Reassessing Semantic Knowledge Encoded in Large Language Models through the Word-in-Context Task",
author = "Hayashi, Yoshihiko",
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.1189",
pages = "13610--13620",
abstract = "Despite the remarkable recent advancements in large language models (LLMs), a comprehensive understanding of their inner workings and the depth of their knowledge remains elusive. This study aims to reassess the semantic knowledge encoded in LLMs by utilizing the Word-in-Context (WiC) task, which involves predicting the semantic equivalence of a target word across different contexts, as a probing task. To address this challenge, we start by prompting LLMs, specifically GPT-3 and GPT-4, to generate natural language descriptions that contrast the meanings of the target word in two contextual sentences given in the WiC dataset. Subsequently, we conduct a manual analysis to examine their linguistic attributes. In parallel, we train a text classification model that utilizes the generated descriptions as supervision and assesses their practical effectiveness in the WiC task. The linguistic and empirical findings reveal a consistent provision of valid and valuable descriptions by LLMs, with LLM-generated descriptions significantly improving classification accuracy. Notably, the highest classification result achieved with GPT-3-generated descriptions largely surpassed GPT-3{'}s zero-shot baseline. However, the GPT-4-generated descriptions performed slightly below GPT-4{'}s zero-shot baseline, suggesting that the full potential of the most advanced large language models, such as GPT-4, is yet to be fully revealed.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hayashi-2024-reassessing">
<titleInfo>
<title>Reassessing Semantic Knowledge Encoded in Large Language Models through the Word-in-Context Task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoshihiko</namePart>
<namePart type="family">Hayashi</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>Despite the remarkable recent advancements in large language models (LLMs), a comprehensive understanding of their inner workings and the depth of their knowledge remains elusive. This study aims to reassess the semantic knowledge encoded in LLMs by utilizing the Word-in-Context (WiC) task, which involves predicting the semantic equivalence of a target word across different contexts, as a probing task. To address this challenge, we start by prompting LLMs, specifically GPT-3 and GPT-4, to generate natural language descriptions that contrast the meanings of the target word in two contextual sentences given in the WiC dataset. Subsequently, we conduct a manual analysis to examine their linguistic attributes. In parallel, we train a text classification model that utilizes the generated descriptions as supervision and assesses their practical effectiveness in the WiC task. The linguistic and empirical findings reveal a consistent provision of valid and valuable descriptions by LLMs, with LLM-generated descriptions significantly improving classification accuracy. Notably, the highest classification result achieved with GPT-3-generated descriptions largely surpassed GPT-3’s zero-shot baseline. However, the GPT-4-generated descriptions performed slightly below GPT-4’s zero-shot baseline, suggesting that the full potential of the most advanced large language models, such as GPT-4, is yet to be fully revealed.</abstract>
<identifier type="citekey">hayashi-2024-reassessing</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1189</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>13610</start>
<end>13620</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Reassessing Semantic Knowledge Encoded in Large Language Models through the Word-in-Context Task
%A Hayashi, Yoshihiko
%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 hayashi-2024-reassessing
%X Despite the remarkable recent advancements in large language models (LLMs), a comprehensive understanding of their inner workings and the depth of their knowledge remains elusive. This study aims to reassess the semantic knowledge encoded in LLMs by utilizing the Word-in-Context (WiC) task, which involves predicting the semantic equivalence of a target word across different contexts, as a probing task. To address this challenge, we start by prompting LLMs, specifically GPT-3 and GPT-4, to generate natural language descriptions that contrast the meanings of the target word in two contextual sentences given in the WiC dataset. Subsequently, we conduct a manual analysis to examine their linguistic attributes. In parallel, we train a text classification model that utilizes the generated descriptions as supervision and assesses their practical effectiveness in the WiC task. The linguistic and empirical findings reveal a consistent provision of valid and valuable descriptions by LLMs, with LLM-generated descriptions significantly improving classification accuracy. Notably, the highest classification result achieved with GPT-3-generated descriptions largely surpassed GPT-3’s zero-shot baseline. However, the GPT-4-generated descriptions performed slightly below GPT-4’s zero-shot baseline, suggesting that the full potential of the most advanced large language models, such as GPT-4, is yet to be fully revealed.
%U https://aclanthology.org/2024.lrec-main.1189
%P 13610-13620
Markdown (Informal)
[Reassessing Semantic Knowledge Encoded in Large Language Models through the Word-in-Context Task](https://aclanthology.org/2024.lrec-main.1189) (Hayashi, LREC-COLING 2024)
ACL