@inproceedings{simov-etal-2026-small,
title = "Small Can Be Beautiful in {LLM}s for {SSH}: a Case for {B}ulgarian",
author = "Simov, Kiril and
Paev, Nikolay and
Osenova, Petya and
Valchev, Teodor and
Marinov, Stefan",
editor = "Montejo-Raez, Arturo and
Grisot, Cristina and
Blochowiak, Joanna and
Ljube{\v{s}}i{\'c}, Nikola and
Battaner, Elena and
Rigau, German",
booktitle = "Proceedings of Shaping Multilingual, Multimodal {AI} for the Social Sciences and Humanities ({LLM}s4{SSH}) @ {LREC} 2026",
month = may,
year = "2026",
address = "Palma de Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.llms4ssh-1.20/",
doi = "10.63317/5n9bq7g3it2s",
pages = "187--197",
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."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="simov-etal-2026-small">
<titleInfo>
<title>Small Can Be Beautiful in LLMs for SSH: a Case for Bulgarian</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kiril</namePart>
<namePart type="family">Simov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikolay</namePart>
<namePart type="family">Paev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Petya</namePart>
<namePart type="family">Osenova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Teodor</namePart>
<namePart type="family">Valchev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stefan</namePart>
<namePart type="family">Marinov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of Shaping Multilingual, Multimodal AI for the Social Sciences and Humanities (LLMs4SSH) @ LREC 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Arturo</namePart>
<namePart type="family">Montejo-Raez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cristina</namePart>
<namePart type="family">Grisot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joanna</namePart>
<namePart type="family">Blochowiak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikola</namePart>
<namePart type="family">Ljubešić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="family">Battaner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">German</namePart>
<namePart type="family">Rigau</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma de Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">simov-etal-2026-small</identifier>
<identifier type="doi">10.63317/5n9bq7g3it2s</identifier>
<location>
<url>https://aclanthology.org/2026.llms4ssh-1.20/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>187</start>
<end>197</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Small Can Be Beautiful in LLMs for SSH: a Case for Bulgarian
%A Simov, Kiril
%A Paev, Nikolay
%A Osenova, Petya
%A Valchev, Teodor
%A Marinov, Stefan
%Y Montejo-Raez, Arturo
%Y Grisot, Cristina
%Y Blochowiak, Joanna
%Y Ljubešić, Nikola
%Y Battaner, Elena
%Y Rigau, German
%S Proceedings of Shaping Multilingual, Multimodal AI for the Social Sciences and Humanities (LLMs4SSH) @ LREC 2026
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma de Mallorca (Spain)
%F simov-etal-2026-small
%X 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.
%R 10.63317/5n9bq7g3it2s
%U https://aclanthology.org/2026.llms4ssh-1.20/
%U https://doi.org/10.63317/5n9bq7g3it2s
%P 187-197
Markdown (Informal)
[Small Can Be Beautiful in LLMs for SSH: a Case for Bulgarian](https://aclanthology.org/2026.llms4ssh-1.20/) (Simov et al., LLMs4SSH 2026)
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).