@inproceedings{kibria-etal-2024-functional,
title = "On Functional Competence of {LLM}s for Linguistic Disambiguation",
author = "Kibria, Raihan and
Dipta, Sheikh Intiser Uddin and
Adnan, Muhammad Abdullah",
editor = "Barak, Libby and
Alikhani, Malihe",
booktitle = "Proceedings of the 28th Conference on Computational Natural Language Learning",
month = nov,
year = "2024",
address = "Miami, FL, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.conll-1.12",
pages = "143--160",
abstract = "We study some Large Language Models to explore their deficiencies in resolving sense ambiguities. In this connection, we evaluate their performance on well-known word sense disambiguation datasets. Word Sense Disambiguation (WSD) has been a long-standing NLP problem, which has given rise to many evaluation datasets and models over the decades. Recently the emergence of Large Language Models (LLM) raises much hope in improving accuracy. In this work, we evaluate word sense disambiguation capabilities of four LLMs: OpenAI{'}s ChatGPT-3.5, Mistral{'}s 7b parameter model, Meta{'}s Llama 70b, and Google{'}s Gemini Pro. We evaluate many well-established datasets containing a variety of texts and senses on these. After observing the performances of some datasets, we selectively study some failure cases and identify the reasons for failures. We explore human judgments that would correct these failures. Our findings suggest that many failure cases are related to a lack of world knowledge and the reasoning to amalgamate this knowledge rather than the lack of linguistic knowledge. We categorize the judgments so that the next generation of LLMs can improve by incorporating deeper world knowledge and reasoning. We conclude that word sense disambiguation could serve as a guide for probing the reasoning power of LLMs to measure their functional competency. We also list the accuracy of these datasets. We find that on many occasions, accuracy drops to below 70{\%}, which is much less than that of well-performing existing models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kibria-etal-2024-functional">
<titleInfo>
<title>On Functional Competence of LLMs for Linguistic Disambiguation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Raihan</namePart>
<namePart type="family">Kibria</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sheikh</namePart>
<namePart type="given">Intiser</namePart>
<namePart type="given">Uddin</namePart>
<namePart type="family">Dipta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="given">Abdullah</namePart>
<namePart type="family">Adnan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 28th Conference on Computational Natural Language Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Libby</namePart>
<namePart type="family">Barak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Malihe</namePart>
<namePart type="family">Alikhani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, FL, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We study some Large Language Models to explore their deficiencies in resolving sense ambiguities. In this connection, we evaluate their performance on well-known word sense disambiguation datasets. Word Sense Disambiguation (WSD) has been a long-standing NLP problem, which has given rise to many evaluation datasets and models over the decades. Recently the emergence of Large Language Models (LLM) raises much hope in improving accuracy. In this work, we evaluate word sense disambiguation capabilities of four LLMs: OpenAI’s ChatGPT-3.5, Mistral’s 7b parameter model, Meta’s Llama 70b, and Google’s Gemini Pro. We evaluate many well-established datasets containing a variety of texts and senses on these. After observing the performances of some datasets, we selectively study some failure cases and identify the reasons for failures. We explore human judgments that would correct these failures. Our findings suggest that many failure cases are related to a lack of world knowledge and the reasoning to amalgamate this knowledge rather than the lack of linguistic knowledge. We categorize the judgments so that the next generation of LLMs can improve by incorporating deeper world knowledge and reasoning. We conclude that word sense disambiguation could serve as a guide for probing the reasoning power of LLMs to measure their functional competency. We also list the accuracy of these datasets. We find that on many occasions, accuracy drops to below 70%, which is much less than that of well-performing existing models.</abstract>
<identifier type="citekey">kibria-etal-2024-functional</identifier>
<location>
<url>https://aclanthology.org/2024.conll-1.12</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>143</start>
<end>160</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T On Functional Competence of LLMs for Linguistic Disambiguation
%A Kibria, Raihan
%A Dipta, Sheikh Intiser Uddin
%A Adnan, Muhammad Abdullah
%Y Barak, Libby
%Y Alikhani, Malihe
%S Proceedings of the 28th Conference on Computational Natural Language Learning
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, FL, USA
%F kibria-etal-2024-functional
%X We study some Large Language Models to explore their deficiencies in resolving sense ambiguities. In this connection, we evaluate their performance on well-known word sense disambiguation datasets. Word Sense Disambiguation (WSD) has been a long-standing NLP problem, which has given rise to many evaluation datasets and models over the decades. Recently the emergence of Large Language Models (LLM) raises much hope in improving accuracy. In this work, we evaluate word sense disambiguation capabilities of four LLMs: OpenAI’s ChatGPT-3.5, Mistral’s 7b parameter model, Meta’s Llama 70b, and Google’s Gemini Pro. We evaluate many well-established datasets containing a variety of texts and senses on these. After observing the performances of some datasets, we selectively study some failure cases and identify the reasons for failures. We explore human judgments that would correct these failures. Our findings suggest that many failure cases are related to a lack of world knowledge and the reasoning to amalgamate this knowledge rather than the lack of linguistic knowledge. We categorize the judgments so that the next generation of LLMs can improve by incorporating deeper world knowledge and reasoning. We conclude that word sense disambiguation could serve as a guide for probing the reasoning power of LLMs to measure their functional competency. We also list the accuracy of these datasets. We find that on many occasions, accuracy drops to below 70%, which is much less than that of well-performing existing models.
%U https://aclanthology.org/2024.conll-1.12
%P 143-160
Markdown (Informal)
[On Functional Competence of LLMs for Linguistic Disambiguation](https://aclanthology.org/2024.conll-1.12) (Kibria et al., CoNLL 2024)
ACL