Benchmarking Vision-Language Models on Chinese Ancient Documents: From OCR to Knowledge Reasoning Article Swipe

PDF

Haiyang Yu , Yuchuan Wu , Fan Shi , Lei Liao , Jinghui Lu , Xiaodong Ge , Han Wang , Minghan Zhuo , Xuecheng Wu , Xiang Fei , Hao Feng , Guozhi Tang , An-Lan Wang , Hanshen Zhu , Yangfan He , Quanhuan Liang , Liyuan Meng , Chao Feng , Can Huang , Jingqun Tang , Bin Li ·

YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2509.09731

Chinese ancient documents, invaluable carriers of millennia of Chinese history and culture, hold rich knowledge across diverse fields but face challenges in digitization and understanding, i.e., traditional methods only scan images, while current Vision-Language Models (VLMs) struggle with their visual and linguistic complexity. Existing document benchmarks focus on English printed texts or simplified Chinese, leaving a gap for evaluating VLMs on ancient Chinese documents. To address this, we present AncientDoc, the first benchmark for Chinese ancient documents, designed to assess VLMs from OCR to knowledge reasoning. AncientDoc includes five tasks (page-level OCR, vernacular translation, reasoning-based QA, knowledge-based QA, linguistic variant QA) and covers 14 document types, over 100 books, and about 3,000 pages. Based on AncientDoc, we evaluate mainstream VLMs using multiple metrics, supplemented by a human-aligned large language model for scoring.

Related Topics

Concepts

No concepts available.

Metadata

Type: preprint
Language: en
Landing Page: http://arxiv.org/abs/2509.09731
PDF: https://arxiv.org/pdf/2509.09731
OA Status: green
OpenAlex ID: https://openalex.org/W4414591483

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4414591483

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.48550/arxiv.2509.09731

Digital Object Identifier
Title: Benchmarking Vision-Language Models on Chinese Ancient Documents: From OCR to Knowledge Reasoning

Work title
Type: preprint

OpenAlex work type
Language: en

Primary language
Publication year: 2025

Year of publication
Publication date: 2025-09-10

Full publication date if available
Authors: Haiyang Yu, Yuchuan Wu, Fan Shi, Lei Liao, Jinghui Lu, Xiaodong Ge, Han Wang, Minghan Zhuo, Xuecheng Wu, Xiang Fei, Hao Feng, Guozhi Tang, An-Lan Wang, Hanshen Zhu, Yangfan He, Quanhuan Liang, Liyuan Meng, Chao Feng, Can Huang, Jingqun Tang, Bin Li

List of authors in order
Landing page: https://arxiv.org/abs/2509.09731

Publisher landing page
PDF URL: https://arxiv.org/pdf/2509.09731

Direct link to full text PDF
Open access: Yes

Whether a free full text is available
OA status: green

Open access status per OpenAlex
OA URL: https://arxiv.org/pdf/2509.09731

Direct OA link when available
Cited by: 0

Total citation count in OpenAlex

Full payload

id	https://openalex.org/W4414591483
doi	https://doi.org/10.48550/arxiv.2509.09731
ids.doi	https://doi.org/10.48550/arxiv.2509.09731
ids.openalex	https://openalex.org/W4414591483
fwci
type	preprint
title	Benchmarking Vision-Language Models on Chinese Ancient Documents: From OCR to Knowledge Reasoning
biblio.issue
biblio.volume
biblio.last_page
biblio.first_page
topics[0].id	https://openalex.org/T11148
topics[0].field.id	https://openalex.org/fields/32
topics[0].field.display_name	Psychology
topics[0].score	0.8411999940872192
topics[0].domain.id	https://openalex.org/domains/2
topics[0].domain.display_name	Social Sciences
topics[0].subfield.id	https://openalex.org/subfields/3205
topics[0].subfield.display_name	Experimental and Cognitive Psychology
topics[0].display_name	Language, Metaphor, and Cognition
is_xpac	False
apc_list
apc_paid
language	en
locations[0].id	pmh:oai:arXiv.org:2509.09731
locations[0].is_oa	True
locations[0].source.id	https://openalex.org/S4306400194
locations[0].source.issn
locations[0].source.type	repository
locations[0].source.is_oa	True
locations[0].source.issn_l
locations[0].source.is_core	False
locations[0].source.is_in_doaj	False
locations[0].source.display_name	arXiv (Cornell University)
locations[0].source.host_organization	https://openalex.org/I205783295
locations[0].source.host_organization_name	Cornell University
locations[0].source.host_organization_lineage	https://openalex.org/I205783295
locations[0].license
locations[0].pdf_url	https://arxiv.org/pdf/2509.09731
locations[0].version	submittedVersion
locations[0].raw_type	text
locations[0].license_id
locations[0].is_accepted	False
locations[0].is_published	False
locations[0].raw_source_name
locations[0].landing_page_url	http://arxiv.org/abs/2509.09731
locations[1].id	doi:10.48550/arxiv.2509.09731
locations[1].is_oa	True
locations[1].source.id	https://openalex.org/S4306400194
locations[1].source.issn
locations[1].source.type	repository
locations[1].source.is_oa	True
locations[1].source.issn_l
locations[1].source.is_core	False
locations[1].source.is_in_doaj	False
locations[1].source.display_name	arXiv (Cornell University)
locations[1].source.host_organization	https://openalex.org/I205783295
locations[1].source.host_organization_name	Cornell University
locations[1].source.host_organization_lineage	https://openalex.org/I205783295
locations[1].license
locations[1].pdf_url
locations[1].version
locations[1].raw_type	article
locations[1].license_id
locations[1].is_accepted	False
locations[1].is_published
locations[1].raw_source_name
locations[1].landing_page_url	https://doi.org/10.48550/arxiv.2509.09731
indexed_in	arxiv, datacite
authorships[0].author.id	https://openalex.org/A5101650550
authorships[0].author.orcid
authorships[0].author.display_name	Haiyang Yu
authorships[0].author_position	first
authorships[0].raw_author_name	Yu, Haiyang
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5102918313
authorships[1].author.orcid	https://orcid.org/0009-0000-3657-5859
authorships[1].author.display_name	Yuchuan Wu
authorships[1].author_position	middle
authorships[1].raw_author_name	Wu, Yuchuan
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5052376376
authorships[2].author.orcid	https://orcid.org/0000-0001-9329-077X
authorships[2].author.display_name	Fan Shi
authorships[2].author_position	middle
authorships[2].raw_author_name	Shi, Fan
authorships[2].is_corresponding	False
authorships[3].author.id	https://openalex.org/A5036022527
authorships[3].author.orcid	https://orcid.org/0000-0003-1325-2410
authorships[3].author.display_name	Lei Liao
authorships[3].author_position	middle
authorships[3].raw_author_name	Liao, Lei
authorships[3].is_corresponding	False
authorships[4].author.id	https://openalex.org/A5050212540
authorships[4].author.orcid	https://orcid.org/0000-0001-7149-6961
authorships[4].author.display_name	Jinghui Lu
authorships[4].author_position	middle
authorships[4].raw_author_name	Lu, Jinghui
authorships[4].is_corresponding	False
authorships[5].author.id	https://openalex.org/A5061838211
authorships[5].author.orcid	https://orcid.org/0000-0002-4796-0223
authorships[5].author.display_name	Xiaodong Ge
authorships[5].author_position	middle
authorships[5].raw_author_name	Ge, Xiaodong
authorships[5].is_corresponding	False
authorships[6].author.id	https://openalex.org/A5100452675
authorships[6].author.orcid	https://orcid.org/0000-0002-1320-0947
authorships[6].author.display_name	Han Wang
authorships[6].author_position	middle
authorships[6].raw_author_name	Wang, Han
authorships[6].is_corresponding	False
authorships[7].author.id	https://openalex.org/A5119757718
authorships[7].author.orcid
authorships[7].author.display_name	Minghan Zhuo
authorships[7].author_position	middle
authorships[7].raw_author_name	Zhuo, Minghan
authorships[7].is_corresponding	False
authorships[8].author.id	https://openalex.org/A5053734709
authorships[8].author.orcid	https://orcid.org/0000-0001-9897-8776
authorships[8].author.display_name	Xuecheng Wu
authorships[8].author_position	middle
authorships[8].raw_author_name	Wu, Xuecheng
authorships[8].is_corresponding	False
authorships[9].author.id	https://openalex.org/A5100660005
authorships[9].author.orcid	https://orcid.org/0000-0001-8271-1815
authorships[9].author.display_name	Xiang Fei
authorships[9].author_position	middle
authorships[9].raw_author_name	Fei, Xiang
authorships[9].is_corresponding	False
authorships[10].author.id	https://openalex.org/A5005177314
authorships[10].author.orcid	https://orcid.org/0000-0002-0899-0438
authorships[10].author.display_name	Hao Feng
authorships[10].author_position	middle
authorships[10].raw_author_name	Feng, Hao
authorships[10].is_corresponding	False
authorships[11].author.id	https://openalex.org/A5107479624
authorships[11].author.orcid
authorships[11].author.display_name	Guozhi Tang
authorships[11].author_position	middle
authorships[11].raw_author_name	Tang, Guozhi
authorships[11].is_corresponding	False
authorships[12].author.id	https://openalex.org/A5048679011
authorships[12].author.orcid
authorships[12].author.display_name	An-Lan Wang
authorships[12].author_position	middle
authorships[12].raw_author_name	Wang, An-Lan
authorships[12].is_corresponding	False
authorships[13].author.id	https://openalex.org/A5108777130
authorships[13].author.orcid
authorships[13].author.display_name	Hanshen Zhu
authorships[13].author_position	middle
authorships[13].raw_author_name	Zhu, Hanshen
authorships[13].is_corresponding	False
authorships[14].author.id	https://openalex.org/A5100642695
authorships[14].author.orcid	https://orcid.org/0000-0002-3153-5177
authorships[14].author.display_name	Yangfan He
authorships[14].author_position	middle
authorships[14].raw_author_name	He, Yangfan
authorships[14].is_corresponding	False
authorships[15].author.id	https://openalex.org/A5080142698
authorships[15].author.orcid	https://orcid.org/0000-0002-1042-1795
authorships[15].author.display_name	Quanhuan Liang
authorships[15].author_position	middle
authorships[15].raw_author_name	Liang, Quanhuan
authorships[15].is_corresponding	False
authorships[16].author.id	https://openalex.org/A5068765373
authorships[16].author.orcid
authorships[16].author.display_name	Liyuan Meng
authorships[16].author_position	middle
authorships[16].raw_author_name	Meng, Liyuan
authorships[16].is_corresponding	False
authorships[17].author.id	https://openalex.org/A5103124726
authorships[17].author.orcid	https://orcid.org/0000-0003-3636-7210
authorships[17].author.display_name	Chao Feng
authorships[17].author_position	middle
authorships[17].raw_author_name	Feng, Chao
authorships[17].is_corresponding	False
authorships[18].author.id	https://openalex.org/A5059214587
authorships[18].author.orcid	https://orcid.org/0000-0001-8167-6114
authorships[18].author.display_name	Can Huang
authorships[18].author_position	middle
authorships[18].raw_author_name	Huang, Can
authorships[18].is_corresponding	False
authorships[19].author.id	https://openalex.org/A5100681719
authorships[19].author.orcid	https://orcid.org/0000-0003-2577-0119
authorships[19].author.display_name	Jingqun Tang
authorships[19].author_position	middle
authorships[19].raw_author_name	Tang, Jingqun
authorships[19].is_corresponding	False
authorships[20].author.id	https://openalex.org/A5100365206
authorships[20].author.orcid	https://orcid.org/0000-0002-7328-9947
authorships[20].author.display_name	Bin Li
authorships[20].author_position	last
authorships[20].raw_author_name	Li, Bin
authorships[20].is_corresponding	False
has_content.pdf	False
has_content.grobid_xml	False
is_paratext	False
open_access.is_oa	True
open_access.oa_url	https://arxiv.org/pdf/2509.09731
open_access.oa_status	green
open_access.any_repository_has_fulltext	False
created_date	2025-10-10T00:00:00
display_name	Benchmarking Vision-Language Models on Chinese Ancient Documents: From OCR to Knowledge Reasoning
has_fulltext	False
is_retracted	False
updated_date	2025-11-06T06:51:31.235846
primary_topic.id	https://openalex.org/T11148
primary_topic.field.id	https://openalex.org/fields/32
primary_topic.field.display_name	Psychology
primary_topic.score	0.8411999940872192
primary_topic.domain.id	https://openalex.org/domains/2
primary_topic.domain.display_name	Social Sciences
primary_topic.subfield.id	https://openalex.org/subfields/3205
primary_topic.subfield.display_name	Experimental and Cognitive Psychology
primary_topic.display_name	Language, Metaphor, and Cognition
cited_by_count	0
locations_count	2
best_oa_location.id	pmh:oai:arXiv.org:2509.09731
best_oa_location.is_oa	True
best_oa_location.source.id	https://openalex.org/S4306400194
best_oa_location.source.issn
best_oa_location.source.type	repository
best_oa_location.source.is_oa	True
best_oa_location.source.issn_l
best_oa_location.source.is_core	False
best_oa_location.source.is_in_doaj	False
best_oa_location.source.display_name	arXiv (Cornell University)
best_oa_location.source.host_organization	https://openalex.org/I205783295
best_oa_location.source.host_organization_name	Cornell University
best_oa_location.source.host_organization_lineage	https://openalex.org/I205783295
best_oa_location.license
best_oa_location.pdf_url	https://arxiv.org/pdf/2509.09731
best_oa_location.version	submittedVersion
best_oa_location.raw_type	text
best_oa_location.license_id
best_oa_location.is_accepted	False
best_oa_location.is_published	False
best_oa_location.raw_source_name
best_oa_location.landing_page_url	http://arxiv.org/abs/2509.09731
primary_location.id	pmh:oai:arXiv.org:2509.09731
primary_location.is_oa	True
primary_location.source.id	https://openalex.org/S4306400194
primary_location.source.issn
primary_location.source.type	repository
primary_location.source.is_oa	True
primary_location.source.issn_l
primary_location.source.is_core	False
primary_location.source.is_in_doaj	False
primary_location.source.display_name	arXiv (Cornell University)
primary_location.source.host_organization	https://openalex.org/I205783295
primary_location.source.host_organization_name	Cornell University
primary_location.source.host_organization_lineage	https://openalex.org/I205783295
primary_location.license
primary_location.pdf_url	https://arxiv.org/pdf/2509.09731
primary_location.version	submittedVersion
primary_location.raw_type	text
primary_location.license_id
primary_location.is_accepted	False
primary_location.is_published	False
primary_location.raw_source_name
primary_location.landing_page_url	http://arxiv.org/abs/2509.09731
publication_date	2025-09-10
publication_year	2025
referenced_works_count	0
abstract_inverted_index.a	55, 125
abstract_inverted_index.14	103
abstract_inverted_index.To	64
abstract_inverted_index.by	124
abstract_inverted_index.in	21
abstract_inverted_index.of	5, 7
abstract_inverted_index.on	47, 60, 114
abstract_inverted_index.or	51
abstract_inverted_index.to	78, 83
abstract_inverted_index.we	67, 116
abstract_inverted_index.100	107
abstract_inverted_index.OCR	82
abstract_inverted_index.QA)	100
abstract_inverted_index.QA,	95, 97
abstract_inverted_index.and	10, 23, 40, 101, 109
abstract_inverted_index.but	18
abstract_inverted_index.for	57, 73, 130
abstract_inverted_index.gap	56
abstract_inverted_index.the	70
abstract_inverted_index.OCR,	91
abstract_inverted_index.VLMs	59, 80, 119
abstract_inverted_index.face	19
abstract_inverted_index.five	88
abstract_inverted_index.from	81
abstract_inverted_index.hold	12
abstract_inverted_index.only	28
abstract_inverted_index.over	106
abstract_inverted_index.rich	13
abstract_inverted_index.scan	29
abstract_inverted_index.with	37
abstract_inverted_index.3,000	111
abstract_inverted_index.Based	113
abstract_inverted_index.about	110
abstract_inverted_index.first	71
abstract_inverted_index.focus	46
abstract_inverted_index.i.e.,	25
abstract_inverted_index.large	127
abstract_inverted_index.model	129
abstract_inverted_index.tasks	89
abstract_inverted_index.texts	50
abstract_inverted_index.their	38
abstract_inverted_index.this,	66
abstract_inverted_index.using	120
abstract_inverted_index.while	31
abstract_inverted_index.(VLMs)	35
abstract_inverted_index.Models	34
abstract_inverted_index.across	15
abstract_inverted_index.assess	79
abstract_inverted_index.books,	108
abstract_inverted_index.covers	102
abstract_inverted_index.fields	17
abstract_inverted_index.pages.	112
abstract_inverted_index.types,	105
abstract_inverted_index.visual	39
abstract_inverted_index.Chinese	0, 8, 62, 74
abstract_inverted_index.English	48
abstract_inverted_index.address	65
abstract_inverted_index.ancient	1, 61, 75
abstract_inverted_index.current	32
abstract_inverted_index.diverse	16
abstract_inverted_index.history	9
abstract_inverted_index.images,	30
abstract_inverted_index.leaving	54
abstract_inverted_index.methods	27
abstract_inverted_index.present	68
abstract_inverted_index.printed	49
abstract_inverted_index.variant	99
abstract_inverted_index.Chinese,	53
abstract_inverted_index.Existing	43
abstract_inverted_index.carriers	4
abstract_inverted_index.culture,	11
abstract_inverted_index.designed	77
abstract_inverted_index.document	44, 104
abstract_inverted_index.evaluate	117
abstract_inverted_index.includes	87
abstract_inverted_index.language	128
abstract_inverted_index.metrics,	122
abstract_inverted_index.multiple	121
abstract_inverted_index.scoring.	131
abstract_inverted_index.struggle	36
abstract_inverted_index.benchmark	72
abstract_inverted_index.knowledge	14, 84
abstract_inverted_index.millennia	6
abstract_inverted_index.AncientDoc	86
abstract_inverted_index.benchmarks	45
abstract_inverted_index.challenges	20
abstract_inverted_index.documents,	2, 76
abstract_inverted_index.documents.	63
abstract_inverted_index.evaluating	58
abstract_inverted_index.invaluable	3
abstract_inverted_index.linguistic	41, 98
abstract_inverted_index.mainstream	118
abstract_inverted_index.reasoning.	85
abstract_inverted_index.simplified	52
abstract_inverted_index.vernacular	92
abstract_inverted_index.(page-level	90
abstract_inverted_index.AncientDoc,	69, 115
abstract_inverted_index.complexity.	42
abstract_inverted_index.traditional	26
abstract_inverted_index.digitization	22
abstract_inverted_index.supplemented	123
abstract_inverted_index.translation,	93
abstract_inverted_index.human-aligned	126
abstract_inverted_index.understanding,	24
abstract_inverted_index.Vision-Language	33
abstract_inverted_index.knowledge-based	96
abstract_inverted_index.reasoning-based	94
cited_by_percentile_year
countries_distinct_count	0
institutions_distinct_count	21
citation_normalized_percentile