CzechTopic: A Benchmark for Zero-Shot Topic Localization in Historical Czech Documents

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kostelník, Martin, Hradiš, Michal, Dočekal, Martin
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915833089884160
author Kostelník, Martin
Hradiš, Michal
Dočekal, Martin
author_facet Kostelník, Martin
Hradiš, Michal
Dočekal, Martin
contents Topic localization aims to identify spans of text that express a given topic defined by a name and description. To study this task, we introduce a human-annotated benchmark based on Czech historical documents, containing human-defined topics together with manually annotated spans and supporting evaluation at both document and word levels. Evaluation is performed relative to human agreement rather than a single reference annotation. We evaluate a diverse range of large language models alongside BERT-based models fine-tuned on a distilled development dataset. Results reveal substantial variability among LLMs, with performance ranging from near-human topic detection to pronounced failures in span localization. While the strongest models approach human agreement, the distilled token embedding models remain competitive despite their smaller scale. The dataset and evaluation framework are publicly available at: https://github.com/dcgm/czechtopic.
format Preprint
id arxiv_https___arxiv_org_abs_2603_03884
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle CzechTopic: A Benchmark for Zero-Shot Topic Localization in Historical Czech Documents
Kostelník, Martin
Hradiš, Michal
Dočekal, Martin
Computation and Language
Artificial Intelligence
Topic localization aims to identify spans of text that express a given topic defined by a name and description. To study this task, we introduce a human-annotated benchmark based on Czech historical documents, containing human-defined topics together with manually annotated spans and supporting evaluation at both document and word levels. Evaluation is performed relative to human agreement rather than a single reference annotation. We evaluate a diverse range of large language models alongside BERT-based models fine-tuned on a distilled development dataset. Results reveal substantial variability among LLMs, with performance ranging from near-human topic detection to pronounced failures in span localization. While the strongest models approach human agreement, the distilled token embedding models remain competitive despite their smaller scale. The dataset and evaluation framework are publicly available at: https://github.com/dcgm/czechtopic.
title CzechTopic: A Benchmark for Zero-Shot Topic Localization in Historical Czech Documents
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2603.03884