mlsanityData to 14 Oct 2026

Chronos: The AI Co-Historian

arXiv 2604.03553 ↗First posted 4 Apr 2026cs.AI cs.CL cs.DLcited by 0

Not on the map. Why?

Abstract (arXiv)

AI is increasingly supporting, accelerating, and automating scientific discovery across subjects. Yet, the adoption of AI in historical research remains limited due to the lack of specialised solutions for historians. To change this, we introduce Chronos, an AI Co-Historian designed to support historians. It allows researchers to create and customize research workflows through natural-language interaction and share these as Chronos-Extensions with others. Chronos specifically addresses the need of historians for a tool that is specialised, non-technical, highly customizable, and facilitates extensive task evaluation. As a first extension, we introduce Chronos-Extract, which enables researchers to automate the targeted extraction of information from image scans of historical sources. We benchmark Chronos-Extract on three historical source corpora and find that it achieves high task-accuracy across primary sources spanning three centuries and diverse languages, layouts, and typefaces. Chronos is openly available and ready for historians to use on their own primary and secondary sources.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 23 of its 57 references that are in the map. First posted on arXiv 4 Apr 2026.

Builds on

23 of 57 references.

References · 23

  1. 2023Visual Instruction Tuningcited by 7,869
  2. 2025AlphaEvolve: A coding agent for scientific and algorithmic discoverycited by 867
  3. 2023OCRBench: On the Hidden Mystery of OCR in Large Multimodal Modelscited by 476
  4. 2024OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoningcited by 173
  5. 2023Table Meets LLM: Can Large Language Models Understand Structured Table Data? A Benchmark and Empirical Studycited by 116
  6. 2024CC-OCR: A Comprehensive and Challenging OCR Benchmark for Evaluating Large Multimodal Models in Literacycited by 81
  7. 2024Document Parsing Unveiled: Techniques, Challenges, and Prospects for Structured Information Extractioncited by 44
  8. 2025OCR-Reasoning Benchmark: Unveiling the True Capabilities of MLLMs in Complex Text-Rich Image Reasoningcited by 25
  9. 2024READoc: A Unified Benchmark for Realistic Document Structured Extractioncited by 15
  10. 2018Ground Truth for training OCR engines on historical documents in German Fraktur and Early Modern Latincited by 12
  11. 2025DocThinker: Explainable Multimodal Large Language Models with Rule-based Reinforcement Learning for Document Understandingcited by 12
  12. 2023American Stories: A Large-Scale Structured Text Dataset of Historical U.S. Newspaperscited by 11
11 more
  1. 2023Efficient OCR for Building a Diverse Digital Historycited by 10
  2. 2025CHURRO: Making History Readable with an Open-Weight Large Vision-Language Model for High-Accuracy, Low-Cost Historical Text Recognitioncited by 9
  3. 2024Newswire: A Large-Scale Structured Database of a Century of Historical Newscited by 5
  4. 2025SCORE: A Semantic Evaluation Framework for Generative Document Parsingcited by 5
  5. 2024Deep Learning for Economistscited by 4
  6. 2023A Benchmark of Nested Named Entity Recognition Approaches in Historical Structured Documentscited by 3
  7. 2024Structuring Authenticity Assessments on Historical Documents using LLMscited by 2
  8. 2025Multimodal LLMs for Historical Dataset Construction from Archival Image Scans: German Patents (1877-1918)cited by 2
  9. 2026GutenOCR: A Grounded Vision-Language Front-End for Documentscited by 2
  10. 2026OmniOCR: Generalist OCR for Ethnic Minority Languagescited by 2
  11. 2023Entry Separation using a Mixed Visual and Textual Language Model: Application to 19th century French Trade Directoriescited by 1

Built on by

Not cited yet.