EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Veracity‐Oriented Context‐Aware Large Language Models–Based Prompting Optimization for Fake News Detection

Weiqiang Jin, Yang Gao, Tao Tao, Xiujun Wang, Ningwei Wang, Baohai Wu, Biao Zhao

International Journal of Intelligent Systems · 2025-01 · 2025 (1)

DOI: 10.1155/int/5920142 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Intelligent Systems, online erschienen am 15.01.2025. Verfasst von Weiqiang Jin und 6 weiteren Autor:innen. Die Arbeit wurde bisher 50-mal zitiert (Crossref) und nennt 78 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Anhui Provincial Department of Education.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Fake news detection (FND) is a critical task in natural language processing (NLP) focused on identifying and mitigating the spread of misinformation. Large language models (LLMs) have recently shown remarkable abilities in understanding semantics and performing logical inference. However, their tendency to generate hallucinations poses significant challenges in accurately detecting deceptive content, leading to suboptimal performance. In addition, existing FND methods often underutilize the extensive prior knowledge embedded within LLMs, resulting in less effective classification outcomes. To address these issues, we propose the CAPE–FND framework, context‐aware prompt engineering, designed for enhancing FND tasks. This framework employs unique veracity‐oriented context‐aware constraints, background information, and analogical reasoning to mitigate LLM hallucinations and utilizes self‐adaptive bootstrap prompting optimization to improve LLM predictions. It further refines initial LLM prompts through adaptive iterative optimization using a random search bootstrap algorithm, maximizing the efficacy of LLM prompting. Extensive zero‐shot and few‐shot experiments using GPT‐3.5‐turbo across multiple public datasets demonstrate the effectiveness and robustness of our CAPE–FND framework, even surpassing advanced GPT‐4.0 and human performance in certain scenarios. To support further LLM–based FND, we have made our approach’s code publicly available on GitHub (our CAPE–FND code: https://github.com/albert-jin/CAPE-FND [Accessed on 2024.09]).

Förderung

  • Anhui Provincial Department of Education

Zitieren

APA

Jin, W., Gao, Y., Tao, T., Wang, X., Wang, N., Wu, B., & Zhao, B. (2025). Veracity‐Oriented Context‐Aware Large Language Models–Based Prompting Optimization for Fake News Detection. International Journal of Intelligent Systems, 2025(1). https://doi.org/10.1155/int/5920142

Vancouver

Jin W, Gao Y, Tao T, Wang X, Wang N, Wu B, et al. Veracity‐Oriented Context‐Aware Large Language Models–Based Prompting Optimization for Fake News Detection. International Journal of Intelligent Systems. 2025;2025(1). doi:10.1155/int/5920142

BibTeX
@article{Jin2025,
  author = {Jin, Weiqiang and Gao, Yang and Tao, Tao and Wang, Xiujun and Wang, Ningwei and Wu, Baohai and Zhao, Biao},
  title = {Veracity‐Oriented Context‐Aware Large Language Models–Based Prompting Optimization for Fake News Detection},
  journal = {International Journal of Intelligent Systems},
  year = {2025},
  volume = {2025},
  number = {1},
  doi = {10.1155/int/5920142}
}
Kostenlos starten →