CROP: Task Relevance via Counterfactuals for Selective On-Policy Distillation
On-policy distillation (OPD) supervises a student language model on trajectories sampled from its current policy, but assigns equal credit to response tokens with unequal supervision value. Selective OPD addresses this limitation by allocating supervision non-uniformly across response tokens according to their estimated training value. Most existing criteria, however, focus primarily on optimization need, such as uncertainty or teacher-student disagreement, while task relevance, namely whether the supervision is tied to the semantic content of the current input, remains less directly character
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- LinkedLinked via arxiv author · 85%Enhan Li →
“CROP: Task Relevance via Counterfactuals for Selective On-Policy Distillation”
- LinkedLinked via arxiv author · 85%Junhao He →
“CROP: Task Relevance via Counterfactuals for Selective On-Policy Distillation”
- LinkedLinked via arxiv author · 85%Hongyang Du →
“CROP: Task Relevance via Counterfactuals for Selective On-Policy Distillation”