Open Models Almanac
Methodstraining objectivedistillation objective

specific method · filed under training objective

Reverse KL divergence

Reverse KL divergence is a loss function used in the multi-teacher on-policy distillation mechanism.1 It is used to formalize the multi-teacher distillation as an on-policy reinforcement learning objective.2

How this definition was written

Summarised by glm-5.3-flash from 1 source; every sentence is checked against the quote it cites.

  1. The reverse KL divergence loss between student and teacher is defined as — MiMo-V2-Flash Technical Report
  2. we cast multi-teacher distillation as an on-policy reinforcement learning objective — MiMo-V2-Flash Technical Report

Also called reverse KL divergence loss, Reverse-KL on-policy distillation, The student minimizes the reverse KL.

sources
2
models
3
labs adopt it
2
strongest
core

Documented in

Evidence

2 quotes from 2 sources, one card per model, each opening with its strongest.

How sources treat it
used 1core 1
↑