Strip the prompt, re-score: SA-OPD filters distillation tokens whose signal survives without the input

When Teachers Mislead: Spurious-Signal-Aware On-Policy Distillation

Yinuo Jiang, Yongjie Ye, Zhou Tao, Xiang Zhuang, Qiang Zhang, Huajun Chen, Tiankai Li

cs.AI

2026-08-04

Distillation teachers can follow template priors over the input. SA-OPD adds a no-prompt forward pass, drops high-gradient tokens whose signal barely changes, and lifts VLM scores 3.5 on average.

What problem this solves

On-policy distillation (OPD) has the student roll out its own trajectories while the teacher gives dense token-level supervision, which is more efficient than sparse sequence-level rewards. Recent selective OPD goes further, prioritizing tokens that are confident, informative, or learnable.

These methods share a blind spot: a teacher's judgment at a token may not be driven by the current input at all, but propped up by language priors, formatting conventions, or stereotyped reasoning templates. The authors call such optimization-relevant but weakly input-grounded supervision a spurious signal. It produces large gradients with almost no task direction, a pure nuisance gradient that also drifts the parameters.

Method

The core of SA-OPD is an input-groundedness proxy: a way to tell whether a token's distillation signal actually depends on the input.

The ideal measure is the conditional mutual information between input and signal, but it has no closed form. The proxy is direct: for each token, recompute the teacher-student divergence once more with the prompt removed, keeping the student's generated prefix. If the signal truly depends on the input, removing the prompt should change it noticeably; if it barely changes, the judgment is template-driven and would say the same for any input. The gap between the two passes is the groundedness; a small gap means a spurious signal.

Groundedness alone is not enough. The authors define a spurious signal as two conditions together: low groundedness (signal does not depend on input) and large divergence magnitude (high optimization impact). Filtering on divergence alone would kill useful, grounded high-divergence tokens; filtering on groundedness alone would over-remove low-impact noise. Intersecting the two axes hits only the most harmful tokens, the large-gradient ones that are not grounded.

A dynamic bound on removed gradient mass keeps the filter from deleting too much at once.

Results

The main runs use Qwen3-4B-Instruct to Qwen3-1.7B (LLM) and Qwen3.5-35B-A3B to Qwen3.5-2B (VLM).

On VLM, visual-understanding average rises from Vanilla OPD's 50.5 to SA-OPD's 54.0 (+3.5), and visual reasoning from 60.4 to 63.5 (+3.1), best on all six subtasks. The largest single-task gain is CountQA, 26.4 to 33.6 (+7.2).

SettingVis. understandingVis. reasoning
Vanilla OPD50.560.4
TIP (best rival)52.361.6
SA-OPD54.063.5

LLM math gains are more modest, average 28.5 to 30.4 (+1.9), with Math500 rising 66.4 to 69.6. The authors' read: on VLM tasks spurious signals are persistent structural contamination, so filtering pays off; on LLM math they behave more like transient noise, so the gain is smaller.

Ablations confirm both axes are needed. Divergence-only scores 69.8, groundedness-only 69.0, SA-OPD 72.2 (Geo3K). Overhead is modest: 2.64% to 7.53% more wall-clock per step than Vanilla OPD, with no extra trainable parameters, just one more teacher and student forward over the prefix.

Why it matters

For anyone running distillation, the takeaway is actionable: a teacher's confidence is not the same as being grounded in the input. Adding a no-prompt forward pass and dropping tokens whose signal survives it is a light, plug-in change, and it pays off most where supervision is dirtiest, namely VLM. It also says signal selection in distillation should watch one more dimension beyond whether a token is learnable: is this judgment actually about the current input.

Limitations

The paper has no dedicated Limitations section; the bounds are scattered. The proxy is an approximation: it measures whether the signal is stable without the prompt, not true mutual information. A fixed selection ratio can be brittle across tasks; the authors mitigate with a dynamic bound, but its beta is tuned seriously only on the counting task. Gains are sensitive to beta, with the CountQA score swinging over a roughly 3-point band. LLM is tested only on math reasoning, with no code, open-ended generation, agent, or multilingual evaluation. About 60% of filtered tokens are content words, so useful signal is dropped on every step by design. No test of non-Qwen families, of teacher and student from different families, or of RLHF settings.

Terms

Source

Related papers

All paper explainers