@inproceedings{yang-etal-2026-changjuan,
title = "{C}hang{J}uan: A Comprehensive Benchmark for Book-Length {C}hinese Story Evaluation",
author = "Yang, Dingyi and
Wang, Mingshuo and
Jin, Qin",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-acl.2044/",
pages = "41116--41134",
ISBN = "979-8-89176-395-1",
abstract = "Automatic evaluation of book-length stories remains underexplored, particularly for non-English literature. We introduce ChangJuan, the first benchmark for *book-length Chinese story evaluation*, comprising 300 novels with metadata, human ratings, and large-scale user reviews. To mitigate the subjectivity of raw reviews, we propose a distillation method to aggregate them into generally agreed viewpoints (pros and cons) across key evaluation aspects such as plot and character. We conduct systematic experiments to benchmark current LLMs, analyze aspect importance, and examine genre differences. For book-length story evaluation, we propose an enhanced summary-based method that leverages length-detail balanced summaries and representative excerpts, generates aspect-specific reviews, and considers genre-aware aspect weighting to assign a final score. Using this framework and our distilled viewpoints, we fine-tune an 8B model, CLEM, which outperforms open-source baselines and raises Qwen3{'}s Kendall{'}s tau correlation with human judgments from 24.8 to 34.1. Our datasets and codes are available at https://github.com/DingyiYang/ChangJuan."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-etal-2026-changjuan">
<titleInfo>
<title>ChangJuan: A Comprehensive Benchmark for Book-Length Chinese Story Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dingyi</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mingshuo</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qin</namePart>
<namePart type="family">Jin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-395-1</identifier>
</relatedItem>
<abstract>Automatic evaluation of book-length stories remains underexplored, particularly for non-English literature. We introduce ChangJuan, the first benchmark for *book-length Chinese story evaluation*, comprising 300 novels with metadata, human ratings, and large-scale user reviews. To mitigate the subjectivity of raw reviews, we propose a distillation method to aggregate them into generally agreed viewpoints (pros and cons) across key evaluation aspects such as plot and character. We conduct systematic experiments to benchmark current LLMs, analyze aspect importance, and examine genre differences. For book-length story evaluation, we propose an enhanced summary-based method that leverages length-detail balanced summaries and representative excerpts, generates aspect-specific reviews, and considers genre-aware aspect weighting to assign a final score. Using this framework and our distilled viewpoints, we fine-tune an 8B model, CLEM, which outperforms open-source baselines and raises Qwen3’s Kendall’s tau correlation with human judgments from 24.8 to 34.1. Our datasets and codes are available at https://github.com/DingyiYang/ChangJuan.</abstract>
<identifier type="citekey">yang-etal-2026-changjuan</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.2044/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>41116</start>
<end>41134</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ChangJuan: A Comprehensive Benchmark for Book-Length Chinese Story Evaluation
%A Yang, Dingyi
%A Wang, Mingshuo
%A Jin, Qin
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F yang-etal-2026-changjuan
%X Automatic evaluation of book-length stories remains underexplored, particularly for non-English literature. We introduce ChangJuan, the first benchmark for *book-length Chinese story evaluation*, comprising 300 novels with metadata, human ratings, and large-scale user reviews. To mitigate the subjectivity of raw reviews, we propose a distillation method to aggregate them into generally agreed viewpoints (pros and cons) across key evaluation aspects such as plot and character. We conduct systematic experiments to benchmark current LLMs, analyze aspect importance, and examine genre differences. For book-length story evaluation, we propose an enhanced summary-based method that leverages length-detail balanced summaries and representative excerpts, generates aspect-specific reviews, and considers genre-aware aspect weighting to assign a final score. Using this framework and our distilled viewpoints, we fine-tune an 8B model, CLEM, which outperforms open-source baselines and raises Qwen3’s Kendall’s tau correlation with human judgments from 24.8 to 34.1. Our datasets and codes are available at https://github.com/DingyiYang/ChangJuan.
%U https://aclanthology.org/2026.findings-acl.2044/
%P 41116-41134
Markdown (Informal)
[ChangJuan: A Comprehensive Benchmark for Book-Length Chinese Story Evaluation](https://aclanthology.org/2026.findings-acl.2044/) (Yang et al., Findings 2026)
ACL