Ancient-Bench: A Comprehensive Multi-millennial, Multi-medium, and Multi-script Benchmark for Ancient Chinese Artifact Text Recognition

• URL: http://arxiv.org/abs/2608.27169v1
• Date: Thu, 27 Aug 2026 14:22:12 GMT
• Title: Ancient-Bench: A Comprehensive Multi-millennial, Multi-medium, and Multi-script Benchmark for Ancient Chinese Artifact Text Recognition
• Abstract summary: Ancient-Bench is a benchmark of 2,700 images for ancient Chinese artifact text recognition.<n>It features three dimensions: Multi-millennial (spanning 3,000 years of character evolution), Multi-medium (covering nine artifact categories), and Multi-script (encompassing seven historical script forms.
• Score: 53.300725050880885
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Ancient Chinese artifact text recognition is fundamental to heritage digitization, and benchmarks for ancient texts are essential for evaluating current model capabilities. However, existing benchmarks suffer from ''fragmentation'', manifested in limited temporal coverage, limited medium diversity, and incomplete script types. Therefore, we present Ancient-Bench, a comprehensive benchmark of 2,700 images for ancient Chinese artifact text recognition, featuring three dimensions: Multi-millennial (spanning 3,000 years of character evolution), Multi-medium (covering nine artifact categories), and Multi-script (encompassing seven historical script forms). To enable consistent and fair evaluation across heterogeneous media, we further define three annotation standards tailored to the medium-specific characteristics of ancient texts: symbol standardization, character standardization, and parsing standardization. Extensive experiments on Ancient-Bench covering general Vision-Language Models (VLMs) and OCR-specialist models reveal that ancient Chinese artifact text recognition remains fundamentally unsolved, with persistent challenges in variant characters, specialized symbols, and hallucination. The dataset is available at https://github.com/SCUT-DLVCLab/Ancient_Bench.

Related papers

• A Text Recognition Dataset from Sahidic Coptic Ancient Manuscripts [43.31909972506497]
  We introduce SCAM (Sahidic Coptic Ancient Manuscripts), a new line-level dataset built from digitized ancient manuscripts written in the extinct Sahidic Coptic dialect.<n>SCAM poses significant linguistic challenges due to the scarcity of resources for Sahidic Coptic, its uncommon alphabet, and dialect-specific diacritics.<n>We benchmark several state-of-the-art approaches based on different paradigms, highlighting their limitations and strengths in this setting.
  arXiv  Detail & Related papers  (2026-06-14T19:26:42Z)
• AncientBench: Towards Comprehensive Evaluation on Excavated and Transmitted Chinese Corpora [20.655514486215196]
  The rapid development of large language models needs benchmarks that can evaluate their comprehension of ancient characters.<n>The AncientBench aims to evaluate the comprehension of ancient characters, especially in the scenario of excavated documents.<n>The benchmark also contains ten tasks, including radical, phonetic radical, homophone, cloze, translation, and more.
  arXiv  Detail & Related papers  (2025-12-19T16:28:57Z)
• Benchmarking Vision-Language Models on Chinese Ancient Documents: From OCR to Knowledge Reasoning [37.68293827920165]
  We present AncientDoc, the first benchmark for Chinese ancient documents, designed to assess Vision-Language Models (VLMs)<n>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.<n>Based on AncientDoc, we evaluate mainstream VLMs using multiple metrics, supplemented by a human-aligned large language model for scoring.
  arXiv  Detail & Related papers  (2025-09-10T13:02:29Z)
• TextVidBench: A Benchmark for Long Video Scene Text Understanding [60.94150574231576]
  We introduce TextVidBench, the first benchmark specifically designed for long-video text question answering (>3 minutes)<n>TextVidBench makes three key contributions: Spanning 9 categories (e.g., news, sports, gaming), with an average video length of 2306 seconds, enabling more realistic evaluation of long-video understanding.<n>We propose an efficient paradigm for improving large models through: (i) introducing the IT-Rope mechanism and temporal prompt engineering to enhance temporal perception, (ii) adopting non-uniform positional encoding to better handle long video sequences, and (iii) applying lightweight fine-tuning on
  arXiv  Detail & Related papers  (2025-06-05T12:54:56Z)
• Beyond Words: Advancing Long-Text Image Generation via Multimodal Autoregressive Models [76.68654868991517]
  Long-form text in images, such as paragraphs in slides or documents, remains a major challenge for current generative models.<n>We introduce a novel text-focused, binary tokenizer optimized for capturing detailed scene text features.<n>We develop ModelName, a multimodal autoregressive model that excels in generating high-quality long-text images with unprecedented fidelity.
  arXiv  Detail & Related papers  (2025-03-26T03:44:25Z)
• Fùxì: A Benchmark for Evaluating Language Models on Ancient Chinese Text Understanding and Generation [20.87296508045343]
  We introduce Fuxi, a comprehensive benchmark that evaluates both understanding and generation capabilities across 21 diverse tasks.<n>We reveal significant performance gaps between understanding and generation tasks, with models achieving promising results in comprehension but struggling considerably in generation tasks.<n>Our findings highlight the current limitations in ancient Chinese text processing and provide insights for future model development.
  arXiv  Detail & Related papers  (2025-03-20T04:26:40Z)
• TextAtlas5M: A Large-scale Dataset for Dense Text Image Generation [88.14715494221123]
  We introduce TextAtlas5M, a novel dataset designed to evaluate long-text rendering in text-conditioned image generation.<n>Our dataset consists of 5 million long-text generated and collected images across diverse data types.<n>We further curate 3000 human-improved test set TextAtlasEval across 3 data domains, establishing one of the most extensive benchmarks for text-conditioned generation.
  arXiv  Detail & Related papers  (2025-02-11T18:59:19Z)
• ASCIIEval: Benchmarking Models' Visual Perception in Text Strings via ASCII Art [83.95594027644124]
  We frame the problem as a recognition task, and construct a novel benchmark, ASCIIEval.<n>It covers over 3K samples with an elaborate categorization tree, along with a training set for further enhancement.<n>Given textual input, language models shows their visual perception ability on ASCII art concepts.<n>For image inputs, we reveal that open-source MLLMs suffer from a trade-off between fine-grained text recognition and collective visual perception.
  arXiv  Detail & Related papers  (2024-10-02T16:46:01Z)
• The Learnable Typewriter: A Generative Approach to Text Analysis [17.355857281085164]
  We present a generative document-specific approach to character analysis and recognition in text lines. Taking as input a set of text lines with similar font or handwriting, our approach can learn a large number of different characters.
  arXiv  Detail & Related papers  (2023-02-03T11:17:59Z)
• LOT: A Benchmark for Evaluating Chinese Long Text Understanding and Generation [49.57366550980932]
  Long text modeling requires many capabilities such as modeling long-range commonsense and discourse relations. We propose LOT, a benchmark including two understanding and two generation tasks for Chinese long text modeling evaluation. We release an encoder-decoder Chinese long text pretraining model named LongLM with up to 1 billion parameters.
  arXiv  Detail & Related papers  (2021-08-30T02:38:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.