@inproceedings{zeng-etal-2024-evaluating-prompting,
title = "Evaluating Prompting Strategies for Grammatical Error Correction Based on Language Proficiency",
author = "Zeng, Min and
Kuang, Jiexin and
Qiu, Mengyang and
Song, Jayoung and
Park, Jungyeul",
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.569",
pages = "6426--6430",
abstract = "This paper proposes an analysis of prompting strategies for grammatical error correction (GEC) with selected large language models (LLM) based on language proficiency. GEC using generative LLMs has been known for overcorrection where results obtain higher recall measures than precision measures. The writing examples of English language learners may be different from those of native speakers. Given that there is a significant differences in second language (L2) learners{'} error types by their proficiency levels, this paper attempts to reduce overcorrection by examining the interaction between LLM{'}s performance and L2 language proficiency. Our method focuses on zero-shot and few-shot prompting and fine-tuning models for GEC for learners of English as a foreign language based on the different proficiency. We investigate GEC results and find that overcorrection happens primarily in advanced language learners{'} writing (proficiency C) rather than proficiency A (a beginner level) and proficiency B (an intermediate level). Fine-tuned LLMs, and even few-shot prompting with writing examples of English learners, actually tend to exhibit decreased recall measures. To make our claim concrete, we conduct a comprehensive examination of GEC outcomes and their evaluation results based on language proficiency.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zeng-etal-2024-evaluating-prompting">
<titleInfo>
<title>Evaluating Prompting Strategies for Grammatical Error Correction Based on Language Proficiency</title>
</titleInfo>
<name type="personal">
<namePart type="given">Min</namePart>
<namePart type="family">Zeng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiexin</namePart>
<namePart type="family">Kuang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mengyang</namePart>
<namePart type="family">Qiu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jayoung</namePart>
<namePart type="family">Song</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jungyeul</namePart>
<namePart type="family">Park</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>This paper proposes an analysis of prompting strategies for grammatical error correction (GEC) with selected large language models (LLM) based on language proficiency. GEC using generative LLMs has been known for overcorrection where results obtain higher recall measures than precision measures. The writing examples of English language learners may be different from those of native speakers. Given that there is a significant differences in second language (L2) learners’ error types by their proficiency levels, this paper attempts to reduce overcorrection by examining the interaction between LLM’s performance and L2 language proficiency. Our method focuses on zero-shot and few-shot prompting and fine-tuning models for GEC for learners of English as a foreign language based on the different proficiency. We investigate GEC results and find that overcorrection happens primarily in advanced language learners’ writing (proficiency C) rather than proficiency A (a beginner level) and proficiency B (an intermediate level). Fine-tuned LLMs, and even few-shot prompting with writing examples of English learners, actually tend to exhibit decreased recall measures. To make our claim concrete, we conduct a comprehensive examination of GEC outcomes and their evaluation results based on language proficiency.</abstract>
<identifier type="citekey">zeng-etal-2024-evaluating-prompting</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.569</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>6426</start>
<end>6430</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluating Prompting Strategies for Grammatical Error Correction Based on Language Proficiency
%A Zeng, Min
%A Kuang, Jiexin
%A Qiu, Mengyang
%A Song, Jayoung
%A Park, Jungyeul
%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 zeng-etal-2024-evaluating-prompting
%X This paper proposes an analysis of prompting strategies for grammatical error correction (GEC) with selected large language models (LLM) based on language proficiency. GEC using generative LLMs has been known for overcorrection where results obtain higher recall measures than precision measures. The writing examples of English language learners may be different from those of native speakers. Given that there is a significant differences in second language (L2) learners’ error types by their proficiency levels, this paper attempts to reduce overcorrection by examining the interaction between LLM’s performance and L2 language proficiency. Our method focuses on zero-shot and few-shot prompting and fine-tuning models for GEC for learners of English as a foreign language based on the different proficiency. We investigate GEC results and find that overcorrection happens primarily in advanced language learners’ writing (proficiency C) rather than proficiency A (a beginner level) and proficiency B (an intermediate level). Fine-tuned LLMs, and even few-shot prompting with writing examples of English learners, actually tend to exhibit decreased recall measures. To make our claim concrete, we conduct a comprehensive examination of GEC outcomes and their evaluation results based on language proficiency.
%U https://aclanthology.org/2024.lrec-main.569
%P 6426-6430
Markdown (Informal)
[Evaluating Prompting Strategies for Grammatical Error Correction Based on Language Proficiency](https://aclanthology.org/2024.lrec-main.569) (Zeng et al., LREC-COLING 2024)
ACL