About this document
LLM Hallucination Survey 2023 Insights by Pratzohol is a document available to read on EtoBox.
This document provides a thorough overview of recent advances in hallucinations generated by large language models (LLMs). It begins with a new taxonomy for classifying LLM hallucinations into factuality and faithfulness types. It then discusses factors contributing to hallucinations and reviews methods for detecting and mitigating hallucinations. The document analyzes challenges and open questions regarding hallucinations in LLMs to guide future research.
- Author
- Pratzohol
- Language
- EN