software-n-erd

joined 2 years ago
sorted by: new top controversial old
[D] With LLMs hallucinating nature, how do we create a credible production ready application? in c/machinelearning@academy.garden
[D] With LLMs hallucinating nature, how do we create a credible production ready application? in c/machinelearning@academy.garden
[–] software-n-erd@alien.top 1 points 2 years ago

Gotcha, I was honestly not aware of any data analysis models. Have you ever used any of them which you think I should look at?

[D] With LLMs hallucinating nature, how do we create a credible production ready application? in c/machinelearning@academy.garden
[–] software-n-erd@alien.top 1 points 2 years ago

I guess people just want to learn. If you think this isn’t the right approach just say it :)

1
[D] With LLMs hallucinating nature, how do we create a credible production ready application? (alien.top)
 

I want to use LLMs to automate analysing data and use it to provide insights to my users, but often times I notice insights being generated on factually incorrect data. I tried fine tuning my prompts, the structure in which I pass data to LLM, few shot learning but there still some chance of it to hallucinate. How can I create a production ready application where this insights are surfaced to end users and presenting incorrect insights is not accepted? I am out of ideas. Any guidance is appreciated 🙏🏻