News for hackers. Stuff that matters.
Re:Finetuning Large Language Models by lukev on Saturday April 22, 2023 @10:51AM (#35667123)
The search+prompt approach has another benefit, which is that allows a chat interface to "cite it's source", something you really can't do with just parameters (fine-tuned or not.)

Although a lot of people are working on hallucination reduction, I think we're a long way off from that in the general case. So having the ability to point to a real piece of data, outside the model, is important for applications where accuracy matters.

Re:Finetuning Large Language Models by vharuck on Saturday April 22, 2023 @12:57PM (#35668548)
I've done that with the rough Q&A tool I made. I include links to websites or documents not so much for verification, but because I work with government info and the devil's in the details. The Q&A is more like a smart search engine, with the summarized answer being a nice bonus.