Hacker News new | ask | show | jobs
by catlifeonmars 20 days ago
What is it about json that models struggle with, in your experience? Is it syntax or structure?
1 comments
chenglong-hn 20 days ago
It's often comes with missing keys, use wrong value type (e.g., list over dictionaries). Mostly a small model issue and open source models, they don't follow instructions on the structure guidance that well, and there is no easy way to do generation-time validation.
link
catlifeonmars 15 days ago
Hmm this is a problem that has long been solved with code completion in a JSON language server and a valid JSON schema.

By this I mean that you can basically tab-complete your way into a valid JSON document matching a particular schema.

Maybe there is a way to restrict the set of output tokens based on the current position in a JSON schema of a JSON document the model is predicting?

link