Comment

Comment by khurdula

We saw that structured decoding didn't make a difference in the quality of the output.

Check out the paper section "6.3 Structured Decoding Ablation"

Paper: https://arxiv.org/pdf/2604.25359

We ran the comparison and saw no difference, so to keep the bench consistent since some models don't support structured decoding we used greedy decoding on all models.

parent khurdula 6 months ago

No comments yet

Be the first to share your thoughts.

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton