This paper examines optical character recognition (OCR) through the lens of archival ethics as outlined in the Society of American Archivists (SAA) Core Values Statement and Code of Ethics, given the current debates surrounding artificial intelligence (AI). A literature review highlights persistent challenges of authenticity and integrity, transparency and accountability, access and equity, and responsible stewardship and sustainability, as well as new concerns about bias, sustainability, and accountability using large language models (LLM). A case study describes systematic testing of LLM, transformer model (TM), and neural network (NN) architectures and examines the challenges in creating a reliable, scalable in-house OCR tool named Opticolumn. This case study finds that NN approaches better align with archival ethics than do LLM tools, which may generate fabrications, but that OCR tool choice will depend on the capacities and preferences of individual institutions.
AllenMarie. 1987. “Optical Character Recognition: Technology with New Relevance for Archival Automation Projects.” The American Archivist50 (1): 94–6. doi:10.17723/aarc.50.1.8j8m4l8q8q2h5p7.
BlankeTobiasBryantMichaelHedgesMark. 2011. “Ocropodium: Open Source OCR for Small- Scale Historical Archives.” Journal of Information Science38 (1): 65–76. doi:10.1177/0165551511429418.
4.
BlankeTobiasBryantMichaelHedgesMark. 2012. “Open Source Optical Character Recognition for Historical Research.” Journal of Documentation68 (5): 613–27. doi:10.1108/00220411211256021.
BurchardtJørgen. 2023. “Are Searches in OCR-Generated Archives Trustworthy? An Analysis of Digital Newspaper Archives.” Economic History Yearbook64 (1): 1–25. doi:10.1515/jbwg-2023-0003.
ChironGuillaumeDoucetAntoineCoustatyMickaelMoreuxJean-Philippe. 2017. “Impact of OCR Errors on the Use of Digital Libraries: Towards a Better Access to Information.” In Proceedings of the 2017 ACM/IEEE Joint Conference on Digital Libraries (JCDL), 277–80. New York, NY: ACM Press. doi:10.1109/JCDL.2017.7991582.
CordellRyan. 2017. “‘Q i-jtb the Raven’: Taking Dirty OCR Seriously.” Book History20: 188–225. doi:10.1353/bh.2017.0006.
11.
DavetJeremyLangelierKarineAngevaareIngeMasSabine. 2023. “Archivist in the Machine: Paradata for AI-Based Automation in the Archives.” Archival Science23: 1–25. doi:10.1007/s10502-023-09408-8.
12.
de OliveiraLucas LimaSimõesGabrielLinsRafael DueireSimskeSteven J.FanJian. 2023. “Evaluating and Mitigating the Impact of OCR Errors on Information Retrieval.” International Journal on Digital Libraries24: 1–22. doi:10.1007/s00799-023-00345-6.
13.
GallagherPatrickGriffinRay. 2025. “Algorithmic Profiling of the Unemployed.” In Digital Public Employment Services in Action, edited by GriffinRayDemazièreDidierLeschkeJanineHansenMagnus Paulsen, 28–43. Bristol: Bristol University Press. doi:10.2307/jj.18323746.7.
14.
Ghaseminejad RaeiniMohammad. 2025. “The Evolution of Language Models: From N-Grams to LLMs, and Beyond.” Natural Language Processing Journal12: 100168. doi:10.1016/j.nlp.2025.100168.
HiltonMichael L.GoesslingJeffrey M.KnezevichLeah M.DownerJane M.2022. “Utility of Machine Learning for Segmenting Camera Trap Time-Lapse Recordings.” Wildlife Society Bulletin46 (4): 1–15. doi:10.1002/wsb.1342.
18.
HuangLeiYuWeijiangMaWeitao, et al. 2025. “A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions.” ACM Transactions on Information Systems43 (2): 42:1–55. doi:10.48550/arXiv.2311.05232.
JaillantLiseReesArran. 2023. “Applying AI to Digital Archives: Trust, Collaboration and Shared Professional Ethics.” Digital Scholarship in the Humanities38 (2): 571–85. doi:10.1093/llc/fqac073.
Keinan-SchoonbaertAdi.2025. “Automatic Text Recognition (OCR/HTR): A LIBER Digital Scholarship & Data Science Topic Guide for Library Professionals.” Digital Scholarship & Data Science Topic Guides. Published electronically May 14, 2025. doi:10.23636/k8qs-wc65.
25.
KhanArshBiswasSanketToluHuseyin. 2024. “OCR Approaches for Humanities: Applications of Artificial Intelligence/Machine Learning on Transcription and Transliteration of Historical Documents.” Digital Studies in Language and Literature1 (1–2): 1–18. doi:10.1515/dsll-2024-0013.
26.
KiesslingBenjamin.2025. The Kraken OCR System. Version 6.0. August 2025. https://kraken.re.
27.
KoeneckeAllisonChoiAnna Seo GyeongMeiKatelyn X.SchellmannHilkeSloaneMona. 2024. “Careless Whisper: Speech-to-Text Hallucination Harms.” In Proceedings of the 2024 ACM Conference on Fairness, Accountability, and Transparency (FAccT ‘24). Association for Computing Machinery, New York, NY, USA. doi:10.1145/3630106.3658996.
28.
MachidonO. M.MachidonA. L.2025. “Comparing OCR Pipelines for Folkloristic Text Digitization.” Digital Heritage. Published electronically. doi:10.48550/arXiv.2507.19092.
29.
MannheimerSaraHigginsDevinNelsonKaylinTannerAllisonStermanLeilaCainJonathanReeseBenjamin. 2024. “Responsible AI Practice in Libraries and Archives: A Review of the Literature.” Information Technology and Libraries43 (3): 1–22. doi:10.5860/ital.v43i3.17245.
30.
McLeodJulieGormlyBrianna. 2017. “Using the Cloud for Records Storage: Issues of Trust.” Archival Science17: 1–22. doi:10.1007/s10502-017-9280-5.
MitaAmandaRadickCarynWellerAnnShaoHsuan. 2018. “CONTENTdm to Digital Commons: Considerations and Workflows.” Journal of Archival Organization15 (1–2): 1–15. doi:10.1080/15332748.2019.1609308.
TraubMyriam C.van OssenbruggenJaccoHardmanLynda. 2015. “Impact Analysis of OCR Quality on Research Tasks in Digital Archives.” In Research and Advanced Technology for Digital Libraries: 19th International Conference on Theory and Practice of Digital Libraries, TPDL 2015, Limerick, Ireland, September 7–11, 2015, edited by AroyoLoraCollierNatalieDiekeAnne R.LangeChristoph, 283–94. Cham: Springer. doi:10.1007/978-3-319-24592-8_19.
University of Idaho Library. 2025a. “About, Dr. Richard B. Wells Collection.” Dr. Richard B. Wells Collection, University of Idaho Digital Collections. https://www.lib.uidaho.edu/digital/wells/about.html.
45.
University of Idaho Library. 2025b. “Digital Collections Search.” https://digital.lib.uidaho.edu (accessed October 1, 2025).
WarnerLiaBelovaPolina. 2025. “Issues in Representing Archives: AI, Ethics, and Metadata: An Interview with Lia Warner.” Comparative Literature Studies62 (3): 493–9. doi:10.5325/complitstudies.62.3.0493.
