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

Enhan Li, Junhao He, Hongyang Du · Aug 13, 2026 · Citations: 0

Open arXiv Find Implementation RSS feed Shortlist (0)

How to use this page

Low trust

Use this as background context only. Do not make protocol decisions from this page alone.

Best use

Background context only

What to verify

Validate the exact study setup in the full paper before operational use.

Evidence quality

Low

Derived from extracted protocol signals and abstract evidence.

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.

Abstract-only analysis — low confidence

All signals on this page are inferred from the abstract only and may be inaccurate. Do not use this page as a primary protocol reference.

This paper looks adjacent to evaluation work, but not like a strong protocol reference.
The available metadata is too thin to trust this as a primary source.
The abstract does not clearly describe the evaluation setup.

Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub

Should You Rely On This Paper?

This paper is adjacent to HFEPX scope and is best used for background context, not as a primary protocol reference.

Best use

Background context only

Use if you need

Background context only.

Main weakness

This paper looks adjacent to evaluation work, but not like a strong protocol reference.

Trust level

Low

Usefulness score

0/100 • Low

Treat as adjacent context, not a core eval-method reference.

Human Feedback Signal

Not explicit in abstract metadata

Evaluation Signal

Weak / implicit signal

Usefulness for eval research

Adjacent candidate

Extraction confidence 30%

If you are doing eval pipeline work, start here:

Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub Tool-Use Eval Hub

What We Could Verify

These are the protocol signals we could actually recover from the available paper metadata. Use them to decide whether this paper is worth deeper reading.

Human Feedback Types

missing

None explicit

No explicit feedback protocol extracted.

"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."

Evaluation Modes

missing

None explicit

Validate eval design from full paper text.

"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."

Quality Controls

partial

Calibration

Calibration/adjudication style controls detected.

"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."

Benchmarks / Datasets

missing

Not extracted

No benchmark anchors detected.

"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."

Reported Metrics

partial

Relevance

Useful for evaluation criteria comparison.

"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."

Human Feedback Details

Uses human feedback: No
Feedback types: None
Rater population: Not reported
Unit of annotation: Trajectory (inferred)
Expertise required: General

Evaluation Details

Evaluation modes:
Agentic eval: None
Quality controls: Calibration
Evidence quality: Low
Use this page as: Background context only

Protocol And Measurement Signals

Benchmarks / Datasets

No benchmark or dataset names were extracted from the available abstract.

Reported Metrics

relevance

Research Brief

Metadata summary

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.

Based on abstract + metadata only. Check the source paper before making high-confidence protocol decisions.

Key Takeaways

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.

Researcher Actions

Compare this paper against nearby papers in the same arXiv category before using it for protocol decisions.
Check the full text for explicit evaluation design choices (raters, protocol, and metrics).
Use related-paper links to find stronger protocol-specific references.

Caveats

Generated from abstract + metadata only; no PDF parsing.
Signals below are heuristic and may miss details reported outside the abstract.

Recommended Queries

Calibration

Research Summary

Contribution Summary

To address this gap, we introduce Counterfactual Relevance for On-Policy Distillation (CROP), which operationalizes task relevance through a paraphrase-calibrated counterfactual sensitivity margin.

Why It Matters For Eval

Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.

Researcher Checklist

Gap: Human feedback protocol is explicit

No explicit human feedback protocol detected.
Gap: Evaluation mode is explicit

No clear evaluation mode extracted.
Pass: Quality control reporting appears

Detected: Calibration
Gap: Benchmark or dataset anchors are present

No benchmark/dataset anchor extracted from abstract.
Pass: Metric reporting is present

Detected: relevance

Related Papers

Papers are ranked by protocol overlap, extraction signal alignment, and semantic proximity.

No related papers found for this item yet.