PERFORMANCE COMPARISON OF ZERO-SHOT AND TWO-SHOT PROMPTING IN DETECTING FAKE NEWS USING LARGE LANGUAGE MODELS
Malaysian Journal of Computer Science · 11.08.2025 · 38 (Special)
DOI: 10.22452/mjcs.vol38spc.8 ↗Kurz gefasst
Fachartikel in der Zeitschrift Malaysian Journal of Computer Science, online erschienen am 11.08.2025. Verfasst von Muhammad Naim Syahmi Roslan und 1 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref).
Abstract (Originalsprache)
Fake news detection is a highly crucial challenge in Natural Language Processing (NLP), particularly during significant social events like elections and national crises. This study uses the GPT-3.5-Turbo model to test the effectiveness of zero-shot and two-shot prompting in detecting fake news on the PolitiFact and Liar datasets. Zero-shot prompting consists of task instructions without examples, whereas two-shot prompting contains a few task-related examples. The methodology includes dataset preparation, Large Language Models (LLMs) response collection, encoding, and evaluation using metrics such as accuracy, precision, recall, and F1-score. The results show that two-shot prompting increases performance marginally across all parameters when compared to zero-shot prompting. PolitiFact’s accuracy improved from 0.286 to 0.293, while Liar’s improved from 0.220 to 0.226. Precision, recall, and F1-score also showed minor gains. However, these advances were not statistically significant and highlight the model’s difficulty with handling multi-class classification in the political domain. The GPT-3.5-Turbo model performed better on the PolitiFact dataset, suggesting variability in performance across different datasets. In conclusion, although two-shot prompting provides a slight advantage, the GPT-3.5-Turbo’s overall performance remains limited, indicating the need for more sophisticated techniques (such as advanced prompting methods or more powerful LLMs) to enhance fake news detection.
Zitieren
APA
Roslan, M. N. S., & Mohd, M. (2025). PERFORMANCE COMPARISON OF ZERO-SHOT AND TWO-SHOT PROMPTING IN DETECTING FAKE NEWS USING LARGE LANGUAGE MODELS. Malaysian Journal of Computer Science, 38(Special). https://doi.org/10.22452/mjcs.vol38spc.8
Vancouver
Roslan MNS, Mohd M. PERFORMANCE COMPARISON OF ZERO-SHOT AND TWO-SHOT PROMPTING IN DETECTING FAKE NEWS USING LARGE LANGUAGE MODELS. Malaysian Journal of Computer Science. 2025;38(Special). doi:10.22452/mjcs.vol38spc.8
BibTeX
@article{Roslan2025,
author = {Roslan, Muhammad Naim Syahmi and Mohd, Masnizah},
title = {PERFORMANCE COMPARISON OF ZERO-SHOT AND TWO-SHOT PROMPTING IN DETECTING FAKE NEWS USING LARGE LANGUAGE MODELS},
journal = {Malaysian Journal of Computer Science},
year = {2025},
volume = {38},
number = {Special},
doi = {10.22452/mjcs.vol38spc.8}
}
EUVIMED