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

Jia-Yu Yao et al. (2023)

Details and statistics

DOI: 10.48550/ARXIV.2310.01469

access: open

type: Informal or Other Publication

metadata version: 2024-01-18

a service of  Schloss Dagstuhl - Leibniz Center for Informatics