LLM Lies: Hallucinations are not Bugs, but Features as Adversarial Examples

Jia-Yu Yao, Kun-Peng Ning, Zhen-Hui Liu +3

Large Language Models (LLMs), including GPT-3.5, LLaMA, and PaLM, seem to be knowledgeable and able to adapt to many tasks. However, we still cannot completely trust their answers,…