Hacker Newsnew | past | comments | ask | show | jobs | submit | broyojo's commentslogin

hmm why can't structured decoding be used?


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.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: