@inproceedings{zou-etal-2026-benchmarking,
title = "Benchmarking Large Language Models for {C}hinese and {J}apanese {IME}s: Phonetic-to-Character Generation and Textual Error Correction",
author = "Zou, Yuchun and
Lee, Tedd and
Fan, Xiaodi and
Li, Jun",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.337/",
doi = "10.63317/42jiimjriyga",
pages = "4290--4311",
abstract = "Efficient text entry for complex writing systems like Chinese and Japanese necessitates the use of Input Method Editors (IMEs). While Large Language Models (LLMs) are emerging as powerful, context-aware language resources for this task, we present a comprehensive benchmark and evaluation methodology to assess the viability of LLMs for next-generation IMEs. We conduct a comparative analysis of a diverse set of LLMs against established baseline methods on two core tasks: phonetic-to-character generation (using Pinyin and Romaji) and textual error correction. Our experiments demonstrate that top-tier LLMs achieve superior accuracy by leveraging deep contextual understanding, significantly outperforming traditional systems in ambiguity resolution and the correction of complex errors. However, our analysis also reveals a crucial trade-off between accuracy and computational efficiency across different models. The datasets, evaluation scripts, and results from this study serve as a vital public resource for future research, providing a robust baseline for developing and selecting models that balance performance with the low-latency demands of real-world text input."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zou-etal-2026-benchmarking">
<titleInfo>
<title>Benchmarking Large Language Models for Chinese and Japanese IMEs: Phonetic-to-Character Generation and Textual Error Correction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuchun</namePart>
<namePart type="family">Zou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tedd</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaodi</namePart>
<namePart type="family">Fan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Efficient text entry for complex writing systems like Chinese and Japanese necessitates the use of Input Method Editors (IMEs). While Large Language Models (LLMs) are emerging as powerful, context-aware language resources for this task, we present a comprehensive benchmark and evaluation methodology to assess the viability of LLMs for next-generation IMEs. We conduct a comparative analysis of a diverse set of LLMs against established baseline methods on two core tasks: phonetic-to-character generation (using Pinyin and Romaji) and textual error correction. Our experiments demonstrate that top-tier LLMs achieve superior accuracy by leveraging deep contextual understanding, significantly outperforming traditional systems in ambiguity resolution and the correction of complex errors. However, our analysis also reveals a crucial trade-off between accuracy and computational efficiency across different models. The datasets, evaluation scripts, and results from this study serve as a vital public resource for future research, providing a robust baseline for developing and selecting models that balance performance with the low-latency demands of real-world text input.</abstract>
<identifier type="citekey">zou-etal-2026-benchmarking</identifier>
<identifier type="doi">10.63317/42jiimjriyga</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.337/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>4290</start>
<end>4311</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Benchmarking Large Language Models for Chinese and Japanese IMEs: Phonetic-to-Character Generation and Textual Error Correction
%A Zou, Yuchun
%A Lee, Tedd
%A Fan, Xiaodi
%A Li, Jun
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F zou-etal-2026-benchmarking
%X Efficient text entry for complex writing systems like Chinese and Japanese necessitates the use of Input Method Editors (IMEs). While Large Language Models (LLMs) are emerging as powerful, context-aware language resources for this task, we present a comprehensive benchmark and evaluation methodology to assess the viability of LLMs for next-generation IMEs. We conduct a comparative analysis of a diverse set of LLMs against established baseline methods on two core tasks: phonetic-to-character generation (using Pinyin and Romaji) and textual error correction. Our experiments demonstrate that top-tier LLMs achieve superior accuracy by leveraging deep contextual understanding, significantly outperforming traditional systems in ambiguity resolution and the correction of complex errors. However, our analysis also reveals a crucial trade-off between accuracy and computational efficiency across different models. The datasets, evaluation scripts, and results from this study serve as a vital public resource for future research, providing a robust baseline for developing and selecting models that balance performance with the low-latency demands of real-world text input.
%R 10.63317/42jiimjriyga
%U https://aclanthology.org/2026.lrec-1.337/
%U https://doi.org/10.63317/42jiimjriyga
%P 4290-4311
Markdown (Informal)
[Benchmarking Large Language Models for Chinese and Japanese IMEs: Phonetic-to-Character Generation and Textual Error Correction](https://aclanthology.org/2026.lrec-1.337/) (Zou et al., LREC 2026)
ACL