Low-resource historical named entity recognition in the era of large language models

Šmajdek, Uroš (author), Munda, Tina (author), Marolt, Matija (author)

We present a comparative evaluation of encoder-based and generative approaches for named entity recognition (NER) on historical Slovene parliamentary records. Using a manually annotated subset of the Carniolan Provincial Assembly Corpus Kranjska 1.0, we evaluate a range of locally deployable open-weight models within a unified multishot prompting framework. Our experiments compare traditional supervised encoderbased systems with modern instruction-tuned generative models across both strict and fuzzy evaluation settings. The results show that larger generative models achieve the best overall performance and demonstrate strong multilingual transfer capabilities, while smaller encoder-based systems remain highly competitive in terms of efficiency, inference speed, and person recognition accuracy. However, all models struggle with the extraction of more ambiguous entity types in historical texts, such as locations and organizations.

• Language: English
• Keywords: digital humanities, historical documents, named entity recognition, large language models
• Work type: Other
• Typology: 1.08 - Published Scientific Conference Contribution
• Organization: FRI - Faculty of Computer and Information Science
• Publication status: Published
• Publication version: Version of Record
• Year: 2026
• Number of pages: Str. 443-462
• PID: 20.500.12556/RUL-189467
• UDC: 004.8:81'33:930.2
• COBISS.SI-ID: 293950979
• Publication date in RUL: 07.10.2026

Record is a part of a monograph

• Title: Zbornik konference Jezikovne tehnologije in digitalna humanistika : 17.-18. september 2026, Ljubljana, Slovenija
• Editors: Špela Arhar Holdt, Vojko Gorjanc, Tomaž Erjavec
• Place of publishing: Ljubljana
• Publisher: Inštitut za novejšo zgodovino, = Institute of Contemporary History
• Year: 2026
• ISBN: 978-961-7104-56-1
• COBISS.SI-ID: 292667395

Licences

• License: CC BY-SA 4.0, Creative Commons Attribution-ShareAlike 4.0 International
• Link: http://creativecommons.org/licenses/by-sa/4.0/
• Description: This Creative Commons license is very similar to the regular Attribution license, but requires the release of all derivative works under this same license.

Secondary language

• Language: Slovenian
• Title: Prepoznavanje zgodovinskih imenskih entitet v jezikih z omejenimi viri v dobi velikih jezikovnih modelov
• Keywords: digitalna humanistika, zgodovinski dokumenti, prepoznavanje imenskih entitet, veliki jezikovni modeli

Projects

• Funder: ARIS - Slovenian Research and Innovation Agency
• Project number: P6-0436-2022
• Name: Digitalna humanistika: viri, orodja in metode

• Funder: ARIS - Slovenian Research and Innovation Agency
• Project number: GC-0002-2024
• Name: Veliki jezikovni modeli za digitalno humanistiko