Hallucination Detection and Hallucination Mitigation: An Investigation

• DOI: 10.48550/arxiv.2401.08358
• Publication Date: 2024-01-01
• Authors: Junliang Luo; Tianyu Li; Di Wu; Michael Jenkin; Steve Liu; Gregory Dudek

Large language models (LLMs), including ChatGPT, Bard, and Llama, have achieved remarkable successes over the last two years in a range of different applications. In spite these successes, there exist concerns that limit wide application LLMs. A key problem is hallucination. Hallucination refers to fact addition correct responses, LLMs can also generate seemingly but factually incorrect responses. This report aims present comprehensive review current literature on both hallucination detection mitigation. We hope this serve as good reference for engineers researchers who are interested applying them real world tasks.