Hallucination Detection and Hallucination Mitigation: An Investigation
It addresses the problem of hallucination for engineers and researchers using LLMs in real-world applications, but is incremental as it is a review.
The paper reviews existing literature on detecting and mitigating hallucinations in large language models, which generate factually incorrect responses, but does not present new experimental results or specific numbers.
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 of these successes, there exist concerns that limit the wide application of LLMs. A key problem is the problem of hallucination. Hallucination refers to the fact that in addition to correct responses, LLMs can also generate seemingly correct but factually incorrect responses. This report aims to present a comprehensive review of the current literature on both hallucination detection and hallucination mitigation. We hope that this report can serve as a good reference for both engineers and researchers who are interested in LLMs and applying them to real world tasks.