Code Hallucination
- What is code hallucination: Generative models such as large language models are extensively used as code copilots and for whole program generation. However, the programs they generate and update may suffer from hallucination.
- In this work, we present several types of code hallucination. We have generated such hallucinated code manually using large language models.
- We present a technique - HallTrigger, in order to demonstrate efficient ways of generating arbitrary code hallucination.
- Our method leverages 3 different dynamic attributes of LLMs to craft prompts that can successfully trigger hallucinations from models without the need to access model architecture or parameters.
- Results from popular blackbox models suggest that HallTrigger is indeed effective and the pervasive LLM hallucination have sheer impact on software development.
- Paper: "Code Hallucination", Mirza Rahman, Ashish Kundu, Ramana Kompella, Elisa Bertino, July '24,https://arxiv.org/abs/2407.04831