@inproceedings{li-etal-2026-boyaeval,
title = "{B}o{Y}a{E}val: Evaluating Multimodal Large Language Models on Understanding {A}ncient {C}hinese Musical Scores",
author = "Li, Jiajia and
Xue, Weizhi and
Yao, Yao and
Li, Qiwei and
Chenchong and
Li, Zuchao and
Wang, Ping and
Zhao, Hai",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-long.997/",
pages = "21858--21873",
ISBN = "979-8-89176-390-6",
abstract = "Multimodal Large Language Models (MLLMs) excel in general tasks but struggle with specialized, structured cultural symbols. We introduce BoYaEval, the first comprehensive benchmark dedicated to deciphering diverse Ancient Chinese musical notations, including five types of ancient Chinese music notation systems. These systems utilize unique spatial layouts and specialized ideograms to encode pitch and intricate playing techniques. BoYaEval comprises 3,175 high-quality images across these notation styles and establishes a three-tier evaluation: Structural Parsing (symbol recognition), Instructional Translation (technique mapping), and Musical Reasoning (melody derivation). We evaluate 21 leading MLLMs. Results indicate that while models perform adequately in basic recognition, they fail in cross-system compositional logic, scoring only around 27{\%} on reasoning tasks. BoYaEval highlights the limitations of current MLLMs in processing diverse spatial-symbolic dependencies, bridging the gap between ancient wisdom and modern AI for digitizing intangible cultural heritage. The BoYaEval benchmark is publicly available at https://huggingface.co/datasets/MYTH-Lab/BoYaEval."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2026-boyaeval">
<titleInfo>
<title>BoYaEval: Evaluating Multimodal Large Language Models on Understanding Ancient Chinese Musical Scores</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jiajia</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weizhi</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yao</namePart>
<namePart type="family">Yao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qiwei</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name>
<namePart>Chenchong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zuchao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ping</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hai</namePart>
<namePart type="family">Zhao</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>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</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">979-8-89176-390-6</identifier>
</relatedItem>
<abstract>Multimodal Large Language Models (MLLMs) excel in general tasks but struggle with specialized, structured cultural symbols. We introduce BoYaEval, the first comprehensive benchmark dedicated to deciphering diverse Ancient Chinese musical notations, including five types of ancient Chinese music notation systems. These systems utilize unique spatial layouts and specialized ideograms to encode pitch and intricate playing techniques. BoYaEval comprises 3,175 high-quality images across these notation styles and establishes a three-tier evaluation: Structural Parsing (symbol recognition), Instructional Translation (technique mapping), and Musical Reasoning (melody derivation). We evaluate 21 leading MLLMs. Results indicate that while models perform adequately in basic recognition, they fail in cross-system compositional logic, scoring only around 27% on reasoning tasks. BoYaEval highlights the limitations of current MLLMs in processing diverse spatial-symbolic dependencies, bridging the gap between ancient wisdom and modern AI for digitizing intangible cultural heritage. The BoYaEval benchmark is publicly available at https://huggingface.co/datasets/MYTH-Lab/BoYaEval.</abstract>
<identifier type="citekey">li-etal-2026-boyaeval</identifier>
<location>
<url>https://aclanthology.org/2026.acl-long.997/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>21858</start>
<end>21873</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BoYaEval: Evaluating Multimodal Large Language Models on Understanding Ancient Chinese Musical Scores
%A Li, Jiajia
%A Xue, Weizhi
%A Yao, Yao
%A Li, Qiwei
%A Li, Zuchao
%A Wang, Ping
%A Zhao, Hai
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%A Chenchong
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-390-6
%F li-etal-2026-boyaeval
%X Multimodal Large Language Models (MLLMs) excel in general tasks but struggle with specialized, structured cultural symbols. We introduce BoYaEval, the first comprehensive benchmark dedicated to deciphering diverse Ancient Chinese musical notations, including five types of ancient Chinese music notation systems. These systems utilize unique spatial layouts and specialized ideograms to encode pitch and intricate playing techniques. BoYaEval comprises 3,175 high-quality images across these notation styles and establishes a three-tier evaluation: Structural Parsing (symbol recognition), Instructional Translation (technique mapping), and Musical Reasoning (melody derivation). We evaluate 21 leading MLLMs. Results indicate that while models perform adequately in basic recognition, they fail in cross-system compositional logic, scoring only around 27% on reasoning tasks. BoYaEval highlights the limitations of current MLLMs in processing diverse spatial-symbolic dependencies, bridging the gap between ancient wisdom and modern AI for digitizing intangible cultural heritage. The BoYaEval benchmark is publicly available at https://huggingface.co/datasets/MYTH-Lab/BoYaEval.
%U https://aclanthology.org/2026.acl-long.997/
%P 21858-21873
Markdown (Informal)
[BoYaEval: Evaluating Multimodal Large Language Models on Understanding Ancient Chinese Musical Scores](https://aclanthology.org/2026.acl-long.997/) (Li et al., ACL 2026)
ACL
- Jiajia Li, Weizhi Xue, Yao Yao, Qiwei Li, Chenchong, Zuchao Li, Ping Wang, and Hai Zhao. 2026. BoYaEval: Evaluating Multimodal Large Language Models on Understanding Ancient Chinese Musical Scores. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 21858–21873, San Diego, California, United States. Association for Computational Linguistics.