@xennygrimmato_: if you’re wondering how token-level rejection sampling works in this paper, here’s how they do it: M_t = max_v [ pi_the…

X AI KOLs Timeline Papers

Summary

Explains token-level rejection sampling for RLHF/PPO, where importance ratio M_t is the maximum over vocabulary and tokens are accepted with Bernoulli sampling based on w_t / M_t.

if you’re wondering how token-level rejection sampling works in this paper, here’s how they do it: M_t = max_v [ pi_theta(v) / pi_old(v) ] z_t ~ Bernoulli( w_t / M_t ) w̃_t = 1 if z_t=1 else w_t L(θ) = E[ Σₜ w̃_t(θ) · Âₜ ] M_t is the max importance ratio across the vocabulary. w_t is the importance ratio for the i-th token. Âₜ comes from GRPO/PPO.
Original Article
View Cached Full Text

Cached at: 07/11/26, 07:28 PM

if you’re wondering how token-level rejection sampling works in this paper, here’s how they do it:

M_t = max_v [ pi_theta(v) / pi_old(v) ] z_t ~ Bernoulli( w_t / M_t ) w̃_t = 1 if z_t=1 else w_t L(θ) = E[ Σₜ w̃_t(θ) · Âₜ ]

M_t is the max importance ratio across the vocabulary. w_t is the importance ratio for the i-th token. Âₜ comes from GRPO/PPO.

Rosinality (@rosinality): https://t.co/o4bRt58hDD

Using rejection sampling to consider accepted tokens as on-policy ones.

Similar Articles