Can I read De-Hallucinator: Mitigating LLM Hallucinations in Code Generation Tasks via Iterative Grounding on EtoBox?

De-Hallucinator: Mitigating LLM Hallucinations in Code Generation Tasks via Iterative Grounding by Eghbali, Aryaz; Pradel, Michael is a scholarly article available to read on EtoBox.

What is De-Hallucinator: Mitigating LLM Hallucinations in Code Generation Tasks via Iterative Grounding about?

Large language models (LLMs) trained on datasets of publicly available source code have established a new state of the art in code generation tasks. However, these models are mostly unaware of the code that exists within a specific project, preventing the models from making good use of existing APIs. Instead, LLMs often invent, or "hallucinate", non-existent APIs or produce variants of already existing code. This paper presents De-Hallucinator, a technique that grounds the predictions of an LLM through a novel combination of retrieving suitable API references and iteratively querying the model with increasingly suitable context information in the prompt. The approach exploits the observation that predictions by LLMs often resemble the desired code, but they fail to correctly refer to already existing APIs. De-Hallucinator automatically identifies project-specific API references related to the model's initial predictions and adds these references into the prompt. Unlike retrieval-augmented generation (RAG), our approach uses the initial prediction(s) by the model to iteratively retrieve increasingly suitable API references. Our evaluation applies the approach to two tasks: predictin

Author

Eghbali, Aryaz; Pradel, Michael

Published

2024

Language

EN