This repository contains a survey paper titled “Siren’s Song in the AI Ocean: A Survey on Hallucination in Large Language Models” along with a curated reading list on the topic. It addresses the problem where LLMs generate plausible but incorrect content that conflicts with user input, context, or factual knowledge. The survey covers methods for evaluating hallucination, explanations for why it occurs, and approaches to mitigate it in real-world deployments.