New ChatGPT bot is out, promises to hallucinate less
OpenAI is bringing us GPT-4, the next evolution of everyone's favourite chatbot, ChatGPT. On top of a more advanced language model that «exhibits human-level performance on various professional and academic tests» the new version accepts image inputs, and promises more stringent refusal behaviour to stop it from fulfilling your untoward requests.
The accompanying GPT-4 Technical Report(opens in new tab) (PDF) warns, however, that the new model still has a relatively high capacity for what the researchers are calling «hallucinations». Which sounds totally safe.
What the researchers mean when they refer to hallucinations is that the new ChatGPT model, much like the previous version, has the tendency to «produce content that is nonsensical or untruthful in relation to certain sources.»
Though the researchers make it clear that «GPT-4 was trained to reduce the model’s tendency to hallucinate by leveraging data from prior models such as ChatGPT.» Not only are they training it on its own fumbles, then, but they've also been training it through human evaluation(opens in new tab).
«We collected real-world data that had been flagged as not being factual, reviewed it, and created a ’factual’ set for it where it was possible to do so. We used this to assess model generations in relation to the ’factual’ set, and facilitate human evaluations.»
The process appears to have helped significantly when it comes to closed topics, though the chatbot is still having trouble when it comes to the broader strokes. As the paper notes, GPT-4 is 29% better than GPT-3.5 when it comes to 'closed-domain' chats, but only 19% better at avoiding 'open-domain' hallucinations.
ITNEXT(opens in new tab) explains the difference between open- and
Read more on pcgamer.com
