Blog – Alonso Astroza Tagle

Sign up using this form to receive an email whenever I post new content on my blog.

Structured Generation Benchmark

Testing LLM’s function-calling capabilities.

LLM

structured-generation

benchmark

function-calling

evals

This report originates from the Outlines community’s proposal to find a good dataset for evaluating structured generation. If you want to participate, join our Discord.