Small Can Be Beautiful in LLMs for SSH: a Case for Bulgarian

Kiril Simov, Nikolay Paev, Petya Osenova, Teodor Valchev, Stefan Marinov


Abstract
In the paper we present a set of small LLM-based models for solving the basic NLP tasks for Bulgarian - POS tagging, Lemmatization, Dependency parsing, Named Entity Recognition, Named Entity Linking, Event Annotation, among others. In order to create fine-tuned models for these tasks, we first pre-train models using architectures like BERT, Modern-BERT, and T5 with different sizes, over Bulgarian data only. For each of the tasks we report our approach towards the fine-tuning, the results from the experiments and also the evaluation. Then we define a way to visualize the results over HTML documents which contain the analyzed texts. Our rationale are as follows: most, if not all SSH research scenarios, need a reliable processing chains that can be customized with respect to the specific needs. These scenarios also would need proper visualization for human observation. We aim to provide such a basic LLM-based toolkit.
Anthology ID:
2026.llms4ssh-1.20
Volume:
Proceedings of Shaping Multilingual, Multimodal AI for the Social Sciences and Humanities (LLMs4SSH) @ LREC 2026
Month:
May
Year:
2026
Address:
Palma de Mallorca (Spain)
Editors:
Arturo Montejo-Raez, Cristina Grisot, Joanna Blochowiak, Nikola Ljubešić, Elena Battaner, German Rigau
Venues:
LLMs4SSH | WS
SIG:
Publisher:
ELRA Language Resources Association (ELRA)
Note:
Pages:
187–197
Language:
External URL:
https://lrec.elra.info/lrec2026-ws-llms4ssh-20
DOI:
10.63317/5n9bq7g3it2s
Bibkey:
Cite (ACL):
Kiril Simov, Nikolay Paev, Petya Osenova, Teodor Valchev, and Stefan Marinov. 2026. Small Can Be Beautiful in LLMs for SSH: a Case for Bulgarian. In Proceedings of Shaping Multilingual, Multimodal AI for the Social Sciences and Humanities (LLMs4SSH) @ LREC 2026, pages 187–197, Palma de Mallorca (Spain). ELRA Language Resources Association (ELRA).
Cite (Informal):
Small Can Be Beautiful in LLMs for SSH: a Case for Bulgarian (Simov et al., LLMs4SSH 2026)
Copy Citation: