@inproceedings{yin-etal-2024-chinese,
title = "{C}hinese Morpheme-informed Evaluation of Large Language Models",
author = "Yin, Yaqi and
Wang, Yue and
Liu, Yang",
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.281",
pages = "3165--3178",
abstract = "Previous evaluations of large language models (LLMs) focused on the perspective of various tasks or abilities. In this paper, we propose to evaluate from a linguistic viewpoint and argue that morpheme, a potential linguistic feature that captures both word-formation and lexical semantics, is another suitable component for evaluation that remains largely unexplored. In light of this, we construct MorphEval, a morpheme-informed benchmark, including three datasets following the bottom-up levels of characters, words, and sentences in Chinese, and then evaluate representative LLMs with both zero- and few-shot settings under two metrics. From this perspective, we reveal three aspects of issues LLMs nowadays encounter: dysfunctions in morphology and syntax, challenges with the long-tailed distribution of semantics, and difficulties from cultural implications. In these scenarios, even a smaller Chinese-targeted model may outperform ChatGPT, highlighting the actual challenges LLMs face and the necessity of language-specific improvements when applied to non-English languages. This new approach could also help guide model enhancements as well as get extended to other languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yin-etal-2024-chinese">
<titleInfo>
<title>Chinese Morpheme-informed Evaluation of Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaqi</namePart>
<namePart type="family">Yin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</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>Previous evaluations of large language models (LLMs) focused on the perspective of various tasks or abilities. In this paper, we propose to evaluate from a linguistic viewpoint and argue that morpheme, a potential linguistic feature that captures both word-formation and lexical semantics, is another suitable component for evaluation that remains largely unexplored. In light of this, we construct MorphEval, a morpheme-informed benchmark, including three datasets following the bottom-up levels of characters, words, and sentences in Chinese, and then evaluate representative LLMs with both zero- and few-shot settings under two metrics. From this perspective, we reveal three aspects of issues LLMs nowadays encounter: dysfunctions in morphology and syntax, challenges with the long-tailed distribution of semantics, and difficulties from cultural implications. In these scenarios, even a smaller Chinese-targeted model may outperform ChatGPT, highlighting the actual challenges LLMs face and the necessity of language-specific improvements when applied to non-English languages. This new approach could also help guide model enhancements as well as get extended to other languages.</abstract>
<identifier type="citekey">yin-etal-2024-chinese</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.281</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>3165</start>
<end>3178</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Chinese Morpheme-informed Evaluation of Large Language Models
%A Yin, Yaqi
%A Wang, Yue
%A Liu, Yang
%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 yin-etal-2024-chinese
%X Previous evaluations of large language models (LLMs) focused on the perspective of various tasks or abilities. In this paper, we propose to evaluate from a linguistic viewpoint and argue that morpheme, a potential linguistic feature that captures both word-formation and lexical semantics, is another suitable component for evaluation that remains largely unexplored. In light of this, we construct MorphEval, a morpheme-informed benchmark, including three datasets following the bottom-up levels of characters, words, and sentences in Chinese, and then evaluate representative LLMs with both zero- and few-shot settings under two metrics. From this perspective, we reveal three aspects of issues LLMs nowadays encounter: dysfunctions in morphology and syntax, challenges with the long-tailed distribution of semantics, and difficulties from cultural implications. In these scenarios, even a smaller Chinese-targeted model may outperform ChatGPT, highlighting the actual challenges LLMs face and the necessity of language-specific improvements when applied to non-English languages. This new approach could also help guide model enhancements as well as get extended to other languages.
%U https://aclanthology.org/2024.lrec-main.281
%P 3165-3178
Markdown (Informal)
[Chinese Morpheme-informed Evaluation of Large Language Models](https://aclanthology.org/2024.lrec-main.281) (Yin et al., LREC-COLING 2024)
ACL