Crimson AI NewsA CrimsonLingua Network service
EN ع
← Back to news
Research paper Hugging Face

SA-OPD: New Framework Filters Spurious Teacher Signals in On-Policy Distillation

AI By Crimson AI Hugging Face Papers 6 August 2026 · 00:00 39 views
Share: X Telegram

Researchers propose SA-OPD, a spurious-signal-aware framework for on-policy distillation that filters misleading token-level teacher supervision based on input-groundedness and optimization impact, improving LLM and VLM performance.

SA-OPD: New Framework Filters Spurious Teacher Signals in On-Policy Distillation

Key points

On-policy distillation (OPD) is a technique that transfers capabilities from a teacher model to a student by supervising trajectories sampled by the student with dense, token-level teacher signals. Recent selective OPD methods aim to improve this process by prioritizing signals that are confident, informative, or learnable. However, these methods overlook a fundamental failure mode: token-level judgments from language models can be driven by input-agnostic language priors, formatting conventions, or stereotyped reasoning templates rather than task-specific evidence.

To address this, researchers introduce SA-OPD (Spurious-Signal-Aware On-Policy Distillation), a framework that identifies and filters misleading token-level supervision based on two criteria: input-groundedness and optimization impact. SA-OPD uses a lightweight proxy to estimate whether a token-level distillation signal truly depends on the input. It then filters only tokens that exhibit both low input-groundedness and extreme distillation divergence, removing high-impact spurious updates while preserving useful supervision.

The method compares token-level teacher–student divergence under the original input and a residual no-prompt context, providing a simple proxy for input-groundedness without requiring external verification labels or auxiliary judges. This targeted filtering aims to avoid large gradients that contribute little to task improvement.

Extensive experiments on both large language model (LLM) and vision-language model (VLM) settings demonstrate that SA-OPD consistently outperforms Vanilla OPD and competitive selective methods on benchmarks for mathematical reasoning, visual understanding, and visual reasoning. The results establish input-groundedness as a key dimension for OPD supervision selection, offering a practical strategy for more reliable distillation.

Source
Hugging Face · Hugging Face Papers
Related news
Research paper
Hugging Face 31 Aug 2026

Hugging Face Unveils StepGuard: Step-Level Guardrails for Safer AI Agents

StepGuard, a new step-level guard model from Hugging Face, audits agent actions before execution, reducing attack success rates by...

1
Research paper
Hugging Face 31 Aug 2026

Hugging Face Researchers Unveil ABot-Recon for Stable Long-Horizon 3D Reconstruction

ABot-Recon, a new streaming 3D reconstruction model from Hugging Face, achieves stable long-horizon performance using only local t...

1
Research paper
Hugging Face 31 Aug 2026

ContextPilot: Teaching Agents Proactive Context Management via Fine-Grained RL

Hugging Face researchers introduce ContextPilot, a framework that enhances long-horizon agent reasoning by expanding context-editi...

1