pith. sign in

Explain in your own words: Improving reasoning via token- selective dual knowledge distillation.arXiv preprint arXiv:2603.13260

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.LG 2

years

2026 2

verdicts

UNVERDICTED 2

representative citing papers

TIP: Token Importance in On-Policy Distillation

cs.LG · 2026-04-15 · unverdicted · novelty 6.0 · 3 refs

A two-axis taxonomy of student entropy and teacher-student divergence identifies informative tokens in on-policy distillation, allowing near-full performance with 10-50% of tokens.

citing papers explorer

Showing 2 of 2 citing papers.

  • Uni-OPD: Unifying On-Policy Distillation with a Dual-Perspective Recipe cs.LG · 2026-05-05 · unverdicted · none · ref 19

    Uni-OPD unifies on-policy distillation across LLMs and MLLMs with dual-perspective strategies that promote student exploration and enforce order-consistent teacher supervision based on outcome rewards.

  • TIP: Token Importance in On-Policy Distillation cs.LG · 2026-04-15 · unverdicted · none · ref 7 · 3 links

    A two-axis taxonomy of student entropy and teacher-student divergence identifies informative tokens in on-policy distillation, allowing near-full performance with 10-50% of tokens.