I can’t have a tool that makes up stuff an unknown amount of time.
There is a world of research examining hallucination Rates, indicating hallucination rates of 30%+.
With steps to reduce it using RAGs, you could potentially improve the results significantly - last I checked it was 80-90%.
And the failure types aren’t just accuracy, it’s precision, recall, relevance and more.
I want to see a citation for this. And a clear definition for what is a hallucination and what isn't.
https://www.medpagetoday.com/ophthalmology/generalophthalmol....
- Survey of Hallucination in Natural Language Generation](https://arxiv.org/abs/2202.03629) (Ji et al., 2022)
- [How Language Model Hallucinations Can Snowball](https://arxiv.org/abs/2305.13534) (Zhang et al., 2023)
- [A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity](https://arxiv.org/abs/2302.04023) (Bang et al., 2023)
- [Contrastive Learning Reduces Hallucination in Conversations](https://arxiv.org/abs/2212.10400) (Sun et al., 2022)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://arxiv.org/abs/2203.11171) (Wang et al., 2022)
- [SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models](https://arxiv.org/abs/2303.08896) ( Manakul et al., 2023)
Ask it what dark matter is, and it won't invent an answer, it will present existing theories and say that it's unknown.
Ask it about a person you know that isn't in it's data set and it'll tell you it has no information about the person.
Despite the fact that people insist that hallucinations are common and that it will invent answers if it doesn't know something frequently, the truth is that chatgpt doesn't hallucinate that much and will frequently say it doesn't know things.
One of the few cases where I've noticed it inventing things are that it often makes up apis for programming libraries and CLI tools that don't exist, and that's trivially fixable by referring it to documentation.