Widening the Gap: Benchmarking Polish LLMs Against Human Baselines in Deception Detection
Applied Sciences · 22.03.2026 · 16 (6) · 3064
DOI: 10.3390/app16063064 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 22.03.2026. Verfasst von Aleksander Wawer und 1 weiteren Autor:innen. Die Arbeit nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: The National Science Centre Poland.
Abstract (Originalsprache)
Detecting deceptive statements is a complex challenge, particularly in non-English contexts where resources are often limited. This study addresses this problem by evaluating the performance of the Polish Large Language Model (LLM), Bielik-11B-v2.3-Instruct. We utilized a dataset of nearly 1500 true and false statements in Polish. In this data, labels reflect agreement with the author’s views. We assessed the model’s performance across diverse prompting variants, adapter fine-tuning, and their combination. The results demonstrate that, while adapter fine-tuning outperforms zero-shot prompting across both data modalities, the combined approach of prompting and fine-tuning is far superior. It achieves an accuracy of 0.82 on typed utterances, exceeding the previously best machine-learning result of 0.69 and human-level accuracy of 0.54. This highlights a growing disparity between humans’ limited detection capabilities and LLMs’ increasing ability to identify deceit.
Förderung
- The National Science Centre Poland
Zitieren
APA
Wawer, A., & Sarzyńska-Wawer, J. (2026). Widening the Gap: Benchmarking Polish LLMs Against Human Baselines in Deception Detection. Applied Sciences, 16(6), 3064. https://doi.org/10.3390/app16063064
Vancouver
Wawer A, Sarzyńska-Wawer J. Widening the Gap: Benchmarking Polish LLMs Against Human Baselines in Deception Detection. Applied Sciences. 2026;16(6):3064. doi:10.3390/app16063064
BibTeX
@article{Wawer2026,
author = {Wawer, Aleksander and Sarzyńska-Wawer, Justyna},
title = {Widening the Gap: Benchmarking Polish LLMs Against Human Baselines in Deception Detection},
journal = {Applied Sciences},
year = {2026},
volume = {16},
number = {6},
pages = {3064},
doi = {10.3390/app16063064}
}
EUVIMED