Soft Best-of-$n$ Sampling for Model Alignment.
Claudio Mayrink Verdun, Alex Oesterling, Himabindu Lakkaraju, Flvio P. Calmon
Browse the full ISIT paper archive.
Claudio Mayrink Verdun, Alex Oesterling, Himabindu Lakkaraju, Flvio P. Calmon
Browse the full ISIT paper archive.