Fake News Detection: Comparative Evaluation of BERT-like Models and Large Language Models with Generative AI-Annotated Data

TL;DR

This paper compares BERT-like models and large language models for fake news detection, introducing a GPT-4-assisted labeled dataset, and finds BERT models generally perform better, while LLMs are more robust to text perturbations.

Contribution

It presents a new dataset labeled with GPT-4 and human verification, and evaluates the performance of different models and AI annotation methods for fake news detection.

Findings

BERT-like models outperform LLMs in classification accuracy.

LLMs show greater robustness to text perturbations.

AI labels with human supervision improve classification results.

Abstract

Fake news poses a significant threat to public opinion and social stability in modern society. This study presents a comparative evaluation of BERT-like encoder-only models and autoregressive decoder-only large language models (LLMs) for fake news detection. We introduce a dataset of news articles labeled with GPT-4 assistance (an AI-labeling method) and verified by human experts to ensure reliability. Both BERT-like encoder-only models and LLMs were fine-tuned on this dataset. Additionally, we developed an instruction-tuned LLM approach with majority voting during inference for label generation. Our analysis reveals that BERT-like models generally outperform LLMs in classification tasks, while LLMs demonstrate superior robustness against text perturbations. Compared to weak labels (distant supervision) data, the results show that AI labels with human supervision achieve better classification results. This study highlights the effectiveness of combining AI-based annotation with human oversight and demonstrates the performance of different families of machine learning models for fake news detection