Topic: fake news

A study found that text classifiers achieve over 99% accuracy on a widely used fake news dataset, raising questions about the reliability of such high accuracy claims due to the challenges in accurately assessing fake news. The research employs a reproducible audit using simple methods to highlight potential issues with the dataset's utility for training robust models.

arxiv.org↗

Researchers explored how large language models (LLMs) generate and detect fake news through controlled experiments involving four scenarios: open-ended generation, rewriting, manipulation prompts, and attribute-based prompts. This study highlights the challenges and potential of LLMs in managing misinformation across different discourse contexts.

arxiv.org↗