Structured Outputs in LLMs

Re:Structured Outputs in LLMs by ninadpathak on Tuesday September 23, 2025 @09:53AM (#45347065)

You're spot on about the "perfect" JSON bar being unreachable for now. The only consistently reliable method I've seen in the wild is some form of constrained decoding or grammar enforcement—bit brittle, but practical. Sampling will always be fuzzy unless the architecture fundamentally shifts. Anyone claiming zero-validity issues is probably glossing over a ton of downstream QA work.

[ Parent | on HN ]

Re:Structured Outputs in LLMs by joatmon-snoo on Tuesday September 23, 2025 @10:47AM (#45347840)

We’ve had a lot of success implementing schema-aligned parsing in BAML, a DSL that we’ve built to simplify this problem.

We actually don’t like constrained generation as approach - among other issues it limits your ability to use reasoning - and instead the technique we’re using is algorithm-driven error-tolerant output parsing.

https://boundaryml.com/

[ Parent | on HN ]

Re:Structured Outputs in LLMs by maxdo on Tuesday September 23, 2025 @11:56AM (#45348823)

Love your work , thanks ! , 12 factor agent implementation uses your tools too.

[ Parent | on HN ]