pith. sign in

Disentangling reasoning tokens and boilerplate tokens for language model fine-tuning

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.LG 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

On the Position Bias of On-Policy Distillation

cs.LG · 2026-06-21 · unverdicted · novelty 7.0

Importance-weighted on-policy distillation counters position bias by scaling token weights according to cumulative student-teacher distribution discrepancy, improving efficiency and final performance over uniform averaging.

citing papers explorer

Showing 1 of 1 citing paper.

  • On the Position Bias of On-Policy Distillation cs.LG · 2026-06-21 · unverdicted · none · ref 46

    Importance-weighted on-policy distillation counters position bias by scaling token weights according to cumulative student-teacher distribution discrepancy, improving efficiency and final performance over uniform averaging.