Skip to content

CROP: Task Relevance via Counterfactuals for Selective On-Policy Distillation

Aug 2026 · 5 citations · 35 references
Computer Science

TL;DR

Counterfactual Relevance for On-Policy Distillation is introduced, which operationalizes task relevance through a paraphrase-calibrated counterfactual sensitivity margin and establishes CROP as a model-internal, contrast-specific method for allocating token-level supervision.

Abstract

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 characterized as a complementary dimension. To address this gap, we introduce Counterfactual Relevance for On-Policy Distillation (CROP), which operationalizes task relevance through a paraphrase-calibrated counterfactual sensitivity margin. For each source prompt, CROP constructs a validated original-paraphrase-counterfactual triplet, holds the student rollout fixed, and measures each response position by its sensitivity to a task-relevant condition change calibrated by its sensitivity to a meaning-preserving rewrite. Matched selection controls show that CROP identifies more useful supervision positions than random or lowest-relevance selection, while component comparisons confirm the value of both counterfactual sensitivity and paraphrase calibration. Across two teacher-student settings, CROP improves aggregate performance by 1.92 and 2.96 points over the strongest non-CROP selector. These results support task relevance as a complementary criterion for selective OPD and establish CROP as a model-internal, contrast-specific method for allocating token-level supervision.

View source

Similar papers

#machine learning Preprint Oct 2026

Rethinking Relative Policy Differences Transfer of On-Policy Distillation

A unified view is developed in which the log-probability ratio between a proxy expert and a proxy reference defines an implicit reward for KL-regularized policy optimization, which enables any-to-any transfer across models that differ in scale, training stage or generation.

Rong Wu, Dao-Cheng Fu, Yu Yang et al. · 0 citations
#natural language process... Preprint Oct 2026

SAPD: Step-Aligned Privileged Distillation

On-policy post-training can improve large language models by learning from their own trajectories, but requires costly rollout generation. We ask whether fixed demonstrations can support competitive off-policy learning through better supervision. Our premise is that their usefulness depends not only on the training tra...

Tian-Le Wang, Jia-Yu Liu, Rui-Zhi Zhao et al. · 0 citations
#artificial intelligence Preprint Sep 2026

Teacher Should Think Ahead: Adaptive Continuations for Reliable On-Policy Distillation

This work identifies Teacher Uncertainty Contraction (TUC), a systematic phenomenon whereby the teacher's predictive uncertainty decreases as it continues from a student-generated prefix, and proposes Adaptive-Continuations On-Policy Distillation (AC-OPD), which augments informative states along student rollouts with t...

Jin-Gang Zhou, Yu-Yi Zhou, Hai-Yang Guo et al. · 3 citations
#machine learning Preprint Oct 2026

DiffGate: Difficulty-Gated Teacher Guidance for On-Policy Distillation

DiffGate is introduced, an outcome-gated objective that combines GRPO with selective, bounded teacher guidance, and improves pass@8 across all four model--domain settings, demonstrating improved solution coverage under the evaluation protocol.

Karn Tiwari, V. Chordia, P. PrathoshA · 0 citations
#artificial intelligence Preprint Aug 2026

Beyond Teacher Likelihood: Group-Calibrated On-Policy Distillation for Long-Context Reasoning

Group-relative residual calibration can incorporate verifier outcomes without discarding dense token-level guidance, and demonstrates that group-relative residual calibration can incorporate verifier outcomes without discarding dense token-level guidance.

Zhu Zhang, Ji-Xun Wang, Xiao-An Xu et al. · 3 citations

Related blog posts

MIT News · Artificial Intelligence Nov 17, 2026

Learning the language of machine learning

By studying the computational foundations of language learning, Associate Professor Jacob Andreas builds intelligent systems that can communicate effectively with humans.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.