Programme and Accepted Papers

The 10th edition of the Slavic NLP Workshop

Registering for Slavic NLP 2025

2025.aclweb.org/registration

Invited Talk

Keynote Speaker: Giovanni Da San Martino, University of Padova
Title: "You must come to this magnificent talk, everyone will be there!" - an Overview of Persuasion Techniques in NLP: corpora, methods and applications
Abstract: TBA

Accepted Papers

All papers will appear in the Proceedings of Slavic NLP 2025 workshop and will be published in the ACL anthology

Time Schedule

09:00 - 09:10 Introduction
09:10 - 10:30 Long Papers
9:10 - 9:30 - Identifying Filled Pauses in Speech Across South and West Slavic Languages
Nikola Ljubešić, Ivan Porupski, Peter Rupnik and Taja Kuzman
9:30 - 9:50 - GigaEmbeddings — Efficient Russian Language Embedding Model
Egor Ilyich Kolodin, Daria Khomich, Nikita Savushkin, Ianina Anastasia, Minkin Fyodor
9:50 - 10:10 - Towards Open Foundation Language Model and Corpus for Macedonian: A Low-Resource Language
Stefan Krsteski, Borjan Sazdov, Matea Tashkovska, Branislav Gerazov and Hristijan Gjoreski

Short Papers
10:10 - 10:15 - When the Dictionary Strikes Back: A Case Study on Slovak Migration Location Term Extraction and NER via Rule-Based vs. LLM Methods
Miroslav Blšták, Jaroslav Kopčan, Marek Suppa, Samuel Havran, Andrej Findor, Martin Takac and Marian Simko
10:15 - 10:20 - Towards compact and efficient Slovak summarization models
Sebastian Petrik and Giang Nguyen
10:20 - 10:25 - Few-Shot Prompting, Full-Scale Confusion: Evaluating Large Language Models for Humor Detection in Croatian Tweets
Petra Bago and Nikola Bakarić
10:25 - 10:30 - Characterizing Linguistic Shifts in Croatian News via Diachronic Word Embeddings
David Dukić, Ana Barić, Marko Čuljak, Josip Jukić and Martin Tutek
10:30 - 11:00 Coffee break
11:00 - 11:50 Keynote Presentation
"You must come to this magnificent talk, everyone will be there!" - an Overview of Persuasion Techniques in NLP: corpora, methods and applications
Giovanni Da San Martino
11:50 - 12:00 Shared Task Overview
SlavicNLP 2025 Shared Task: Detection and Classification of Persuasion Techniques in Parliamentary Debates and Social Media
Jakub Piskorski, Dimitar Iliyanov Dimitrov, Filip Dobranić, Marina Ernst, Jacek Haneczok, Ivan K. Koychev, Nikola Ljubešić, Michal Marcińczuk, Arkadiusz Modzelewski, Ivo Z. Moravski and Roman Yangarber
12:00 - 12:35 Pitch Presentations - Shared Task Papers
Fine-Tuned Transformers for Detection and Classification of Persuasion Techniques in Slavic Languages
Ekaterina Loginova
Gradient Flush at Slavic NLP 2025 Task: Leveraging Slavic BERT and Translation for Persuasion Techniques Classification
Sergey Senichev, Aleksandr Boriskin, Nikita Krayko and Daria Galimzianova
Empowering Persuasion Detection in Slavic Texts through Two-Stage Generative Reasoning
Xin Zou, Chuhan Wang, Dailin Li, Yanan Wang, Jian Wang and Hongfei Lin
Hierarchical Classification of Propaganda Techniques in Slavic Texts in Hyperbolic Space
Christopher Brückner and Pavel Pecina
Team INSAntive at SlavicNLP-2025 Shared Task: Data Augmentation and Enhancement via Explanations for Persuasion Technique Classification
Yutong Wang, Diana Nurbakova and Sylvie Calabretto
LLMs for Detection and Classification of Persuasion Techniques in Slavic Parliamentary Debates and Social Media Texts
Julia Jose and Rachel Greenstadt
Fine-Tuned Transformer-Based Weighted Ensemble for Binary Classification in Slavic Languages
Mahshar Yahan, Sakib Sarker and Mohammad Amanul Islam
Robust Detection of Persuasion Techniques in Slavic Languages via Multitask Debiasing and Walking Embeddings
Ewelina Księżniak, Krzysztof Węcel and Marcin Sawiński
Multilabel Classification of Persuasion Techniques with self-improving LLM agent: SlavicNLP 2025 Shared Task
Marcin Sawiński, Krzysztof Węcel and Ewelina Księżniak
12:35 - 14:00 Lunch Break
14:00 - 15:35 Long Papers
14:00 - 14:20 REPA: Russian Error Types Annotation for Evaluating Text Generation and Judgment Capabilities
Alexander Pugachev, Alena Fenogenova, Vladislav Mikhailov and Ekaterina Artemova
14:20 - 14:40 Rubic2: Ensemble Model for Russian Lemmatization
Ilia Afanasev, Anna Glazkova, Olga Lyashevskaya, Dmitry Morozov, Ivan Smal and Natalia Vlasova
14:40 - 15:00 PL-Guard: Benchmarking Language Model Safety for Polish
Aleksandra Krasnodębska, Karolina Seweryn, Szymon Łukasik and Wojciech Kusa

Short Papers
15:00 - 15:05 Gender Representation Bias Analysis in LLM-Generated Czech and Slovenian Texts
Erik Derner and Kristina Batistič
15:05 - 15:10 What Makes You CLIC: Detection of Croatian Clickbait Headliness
Marija Andelic, Dominik Sipek, Laura Majer and Jan Snajder
15:10 - 15:15 Dialects, Topic Models, and Border Effects: The Rusyn Case
Achim Rabus and Yves Scherrer
15:15 - 15:20 Adapting Definition Modeling for New Languages: A Case Study on Belarusian
Daniela Kazakouskaya, Timothee Mickus and Janine Siewert
15:20 - 15:25 Bridging the Gap with RedSQL: A Russian Text-to-SQL Benchmark for Domain-Specific Applications
Irina Aleksandrovna Brodskaya, Elena Tutubalina and Oleg Dmitrievich Somov
15:25 - 15:30 Can information theory unravel the subtext in a Chekhovian short story?
J. Nathanael Philipp, Olav Mueller-Reichau, Matthias Irmer, Michael Richter and Max Kölbl
15:30 - 15:35 DIACU: A dataset for the DIAchronic analysis of Church Slavonic
Maria Cassese, Giovanni Puccetti, Marianna Napolitano and Andrea Esuli
15:35 - 16:00 Coffee Break
16:00 - 17:15 Poster Session - Short Papers
Few-Shot Prompting, Full-Scale Confusion: Evaluating Large Language Models for Humor Detection in Croatian Tweets
Petra Bago and Nikola Bakarić
Dialects, Topic Models, and Border Effects: The Rusyn Case
Achim Rabus and Yves Scherrer
Towards compact and efficient Slovak summarization models
Sebastian Petrik and Giang Nguyen
Adapting Definition Modeling for New Languages: A Case Study on Belarusian
Daniela Kazakouskaya, Timothee Mickus and Janine Siewert
Bridging the Gap with RedSQL: A Russian Text-to-SQL Benchmark for Domain-Specific Applications
Irina Aleksandrovna Brodskaya, Elena Tutubalina and Oleg Dmitrievich Somov
Can information theory unravel the subtext in a Chekhovian short story?
J. Nathanael Philipp, Olav Mueller-Reichau, Matthias Irmer, Michael Richter and Max Kölbl
When the Dictionary Strikes Back: A Case Study on Slovak Migration Location Term Extraction and NER via Rule-Based vs. LLM Methods
Miroslav Blšták, Jaroslav Kopčan, Marek Suppa, Samuel Havran, Andrej Findor, Martin Takac and Marian Simko
DIACU: A dataset for the DIAchronic analysis of Church Slavonic
Maria Cassese, Giovanni Puccetti, Marianna Napolitano and Andrea Esuli
Characterizing Linguistic Shifts in Croatian News via Diachronic Word Embeddings
David Dukić, Ana Barić, Marko Čuljak, Josip Jukić and Martin Tutek
What Makes You CLIC: Detection of Croatian Clickbait Headliness
Marija Andelić, Dominik Sipek, Laura Majer and Jan Snajder
Gender Representation Bias Analysis in LLM-Generated Czech and Slovenian Texts
Erik Derner and Kristina Batistič

Poster Session - System Papers
Fine-Tuned Transformers for Detection and Classification of Persuasion Techniques in Slavic Languages
Ekaterina Loginova
Gradient Flush at Slavic NLP 2025 Task: Leveraging Slavic BERT and Translation for Persuasion Techniques Classification
Sergey Senichev, Aleksandr Boriskin, Nikita Krayko and Daria Galimzianova
Empowering Persuasion Detection in Slavic Texts through Two-Stage Generative Reasoning
Xin Zou, Chuhan Wang, Dailin Li, Yanan Wang, Jian Wang and Hongfei Lin
Hierarchical Classification of Propaganda Techniques in Slavic Texts in Hyperbolic Space
Christopher Brückner and Pavel Pecina
Team INSAntive at SlavicNLP-2025 Shared Task: Data Augmentation and Enhancement via Explanations for Persuasion Technique Classification
Yutong Wang, Diana Nurbakova and Sylvie Calabretto
LLMs for Detection and Classification of Persuasion Techniques in Slavic Parliamentary Debates and Social Media Texts
Julia Jose and Rachel Greenstadt
Fine-Tuned Transformer-Based Weighted Ensemble for Binary Classification in Slavic Languages
Mahshar Yahan, Sakib Sarker and Mohammad Amanul Islam
Robust Detection of Persuasion Techniques in Slavic Languages via Multitask Debiasing and Walking Embeddings
Ewelina Księżniak, Krzysztof Węcel and Marcin Sawiński
Multilabel Classification of Persuasion Techniques with self-improving LLM agent: SlavicNLP 2025 Shared Task
Marcin Sawiński, Krzysztof Węcel and Ewelina Księżniak
17:15 - 17:30 Best Papers Awards
17:30 End of the workshop

Accepted Papers for Slavic NLP 2025

PDFs to be provided

Long Papers