Papers by Marek Suppa

8 papers
RAGthoven: A Configurable Toolkit for RAG-enabled LLM Experimentation (2025.coling-demos)

Copied to clipboard

Challenge: Large Language Models (LLMs) have significantly altered the landscape of Natural Language Processing (NLP), but their use as a baseline method has not been extensive.
Approach: They propose a tool for automatic evaluation of RAG-based pipelines that provides a simple yet powerful abstraction.
Outcome: The proposed tool provides an automatic evaluation of RAG-based pipelines.
Universal NER: A Gold-Standard Multilingual Named Entity Recognition Benchmark (2024.naacl-long)

Copied to clipboard

Challenge: In named entity recognition, the majority of annotation efforts are centered on English, and cross-lingual transfer performance remains brittle.
Approach: They propose to develop gold-standard named entity recognition benchmarks in many languages using a cross-lingual consistent schema.
Outcome: The proposed benchmarks will be released to the public in 2022 . they will provide baselines on in-language and cross-lingual learning settings.
SlovakSum: A Large Scale Slovak Summarization Dataset (2024.lrec-main)

Copied to clipboard

Challenge: Existing datasets with hundreds and thousands of documents are mainly in the English language, but the available data is small or non-existent.
Approach: They propose to use a large Slovak news summarization dataset to evaluate its performance . the dataset contains headlines, short abstracts, and full source text .
Outcome: The proposed dataset is compared with a standard ROUGE metric and a mT5 model to evaluate its performance.
Trojsten Benchmark: Evaluating LLM Problem-Solving in Slovak STEM Competition Problems (2025.emnlp-main)

Copied to clipboard

Challenge: Large language models have been used for grading open-ended responses and providing feedback beyond traditional methods.
Approach: They propose a Slovak-language dataset and a rubric-based LLM grading framework . they quantify multistep reasoning performance by difficulty and show consistency under difficult items .
Outcome: The proposed model outperforms existing models on Slovak-language competition problems . the model shows consistent underperformance on harder items and language sensitivity .
skLEP: A Slovak General Language Understanding Benchmark (2025.findings-acl)

Copied to clipboard

Challenge: skLEP is the first comprehensive benchmark specifically designed for evaluating Slovak natural language understanding models.
Approach: They introduce a benchmark specifically designed for evaluating Slovak natural language understanding models.
Outcome: The proposed benchmark covers nine tasks that span token-level, sentence-pair, document-level tasks.
A Summarization Dataset of Slovak News Articles (2020.lrec-1)

Copied to clipboard

Challenge: a number of studies on document summarization have focused on the English language . however, most of the work on this task is done on English datasets .
Approach: They propose to use a news site's ROUGE metric to adapt it to Slovak texts . they propose to introduce a large-scale news-based summarization dataset .
Outcome: The proposed approach is better suited for Slovak texts than the dominant ROUGE metric.
SkMTEB: Slovak Massive Text Embedding Benchmark and Model Adaptation (2026.acl-long)

Copied to clipboard

Challenge: Slovak embeddings are core infrastructure for semantic search, retrieval-augmented generation (RAG), clustering, and classification.
Approach: They propose a MTEB-style text embedding benchmark for Slovak, a low-resource West Slavic language . they use 31 datasets across 7 task types to evaluate the performance of the models .
Outcome: The proposed model achieves competitive performance with proprietary APIs while remaining locally deployable for RAG . the model is based on 31 datasets across 7 task types and is 4 the depth of existing benchmark for Slovak .
Cost-effective Deployment of BERT Models in Serverless Environment (2021.naacl-industry)

Copied to clipboard

Challenge: a large upfront infrastructure investment makes machine learning models difficult to deploy . however, serverless architectures have strict limits on the size of the deployment package .
Approach: They propose to fine-tune BERT-style models on proprietary datasets for tasks . they use knowledge distillation to obtain models that are tuned for a specific domain .
Outcome: The proposed model deployments report acceptable latency levels and cost-effectiveness without infrastructure overhead.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations