@inproceedings{hu-cong-2025-modeling,
title = "Modeling {C}hinese {L}2 Writing Development: The {LLM}-Surprisal Perspective",
author = "Hu, Jingying and
Cong, Yan",
editor = "Kuribayashi, Tatsuki and
Rambelli, Giulia and
Takmaz, Ece and
Wicke, Philipp and
Li, Jixing and
Oh, Byung-Doh",
booktitle = "Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics",
month = may,
year = "2025",
address = "Albuquerque, New Mexico, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.cmcl-1.22/",
doi = "10.18653/v1/2025.cmcl-1.22",
pages = "172--183",
ISBN = "979-8-89176-227-5",
abstract = "LLM-surprisal is a computational measure of how unexpected a word or character is given the preceding context, as estimated by large language models (LLMs). This study investigated the effectiveness of LLM-surprisal in modeling second language (L2) writing development, focusing on Chinese L2 writing as a case to test its cross-linguistical generalizability. We selected three types of LLMs with different pretraining settings: a multilingual model trained on various languages, a Chinese-general model trained on both Simplified and Traditional Chinese, and a Traditional-Chinese-specific model. This comparison allowed us to explore how model architecture and training data affect LLM-surprisal estimates of learners' essays written in Traditional Chinese, which in turn influence the modeling of L2 proficiency and development. We also correlated LLM-surprisals with 16 classic linguistic complexity indices (e.g., character sophistication, lexical diversity, syntactic complexity, and discourse coherence) to evaluate its interpretability and validity as a measure of L2 writing assessment. Our findings demonstrate the potential of LLM-surprisal as a robust, interpretable, cross-linguistically applicable metric for automatic writing assessment and contribute to bridging computational and linguistic approaches in understanding and modeling L2 writing development. All analysis scripts are available at https://github.com/JingyingHu/ChineseL2Writing-Surprisals."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hu-cong-2025-modeling">
<titleInfo>
<title>Modeling Chinese L2 Writing Development: The LLM-Surprisal Perspective</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jingying</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yan</namePart>
<namePart type="family">Cong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tatsuki</namePart>
<namePart type="family">Kuribayashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giulia</namePart>
<namePart type="family">Rambelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ece</namePart>
<namePart type="family">Takmaz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philipp</namePart>
<namePart type="family">Wicke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jixing</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Byung-Doh</namePart>
<namePart type="family">Oh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-227-5</identifier>
</relatedItem>
<abstract>LLM-surprisal is a computational measure of how unexpected a word or character is given the preceding context, as estimated by large language models (LLMs). This study investigated the effectiveness of LLM-surprisal in modeling second language (L2) writing development, focusing on Chinese L2 writing as a case to test its cross-linguistical generalizability. We selected three types of LLMs with different pretraining settings: a multilingual model trained on various languages, a Chinese-general model trained on both Simplified and Traditional Chinese, and a Traditional-Chinese-specific model. This comparison allowed us to explore how model architecture and training data affect LLM-surprisal estimates of learners’ essays written in Traditional Chinese, which in turn influence the modeling of L2 proficiency and development. We also correlated LLM-surprisals with 16 classic linguistic complexity indices (e.g., character sophistication, lexical diversity, syntactic complexity, and discourse coherence) to evaluate its interpretability and validity as a measure of L2 writing assessment. Our findings demonstrate the potential of LLM-surprisal as a robust, interpretable, cross-linguistically applicable metric for automatic writing assessment and contribute to bridging computational and linguistic approaches in understanding and modeling L2 writing development. All analysis scripts are available at https://github.com/JingyingHu/ChineseL2Writing-Surprisals.</abstract>
<identifier type="citekey">hu-cong-2025-modeling</identifier>
<identifier type="doi">10.18653/v1/2025.cmcl-1.22</identifier>
<location>
<url>https://aclanthology.org/2025.cmcl-1.22/</url>
</location>
<part>
<date>2025-05</date>
<extent unit="page">
<start>172</start>
<end>183</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Modeling Chinese L2 Writing Development: The LLM-Surprisal Perspective
%A Hu, Jingying
%A Cong, Yan
%Y Kuribayashi, Tatsuki
%Y Rambelli, Giulia
%Y Takmaz, Ece
%Y Wicke, Philipp
%Y Li, Jixing
%Y Oh, Byung-Doh
%S Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics
%D 2025
%8 May
%I Association for Computational Linguistics
%C Albuquerque, New Mexico, USA
%@ 979-8-89176-227-5
%F hu-cong-2025-modeling
%X LLM-surprisal is a computational measure of how unexpected a word or character is given the preceding context, as estimated by large language models (LLMs). This study investigated the effectiveness of LLM-surprisal in modeling second language (L2) writing development, focusing on Chinese L2 writing as a case to test its cross-linguistical generalizability. We selected three types of LLMs with different pretraining settings: a multilingual model trained on various languages, a Chinese-general model trained on both Simplified and Traditional Chinese, and a Traditional-Chinese-specific model. This comparison allowed us to explore how model architecture and training data affect LLM-surprisal estimates of learners’ essays written in Traditional Chinese, which in turn influence the modeling of L2 proficiency and development. We also correlated LLM-surprisals with 16 classic linguistic complexity indices (e.g., character sophistication, lexical diversity, syntactic complexity, and discourse coherence) to evaluate its interpretability and validity as a measure of L2 writing assessment. Our findings demonstrate the potential of LLM-surprisal as a robust, interpretable, cross-linguistically applicable metric for automatic writing assessment and contribute to bridging computational and linguistic approaches in understanding and modeling L2 writing development. All analysis scripts are available at https://github.com/JingyingHu/ChineseL2Writing-Surprisals.
%R 10.18653/v1/2025.cmcl-1.22
%U https://aclanthology.org/2025.cmcl-1.22/
%U https://doi.org/10.18653/v1/2025.cmcl-1.22
%P 172-183
Markdown (Informal)
[Modeling Chinese L2 Writing Development: The LLM-Surprisal Perspective](https://aclanthology.org/2025.cmcl-1.22/) (Hu & Cong, CMCL 2025)
ACL