When EOS Tokens Disagree: Understanding Length Inflation in On-Policy Distillation

2026-09-17

AI Summary

本文研究了在策略蒸馏中由于终止标记不匹配导致的长度膨胀问题，并通过将功能等效的终止标记视为共享语义停止动作来缓解该问题。

Abstract

We study length inflation in on-policy distillation (OPD), where student responses can become excessively long and even exhaust the generation budget. We identify \emph{termination-token mismatch} between base students and post-trained teachers as an important source of this behavior. Across Qwen3, Llama, and Gemma, the two models can place their stopping probability on different EOS tokens, even when their declared stopping sets are identical. This mismatch can suppress the student's preferred termination action without reliably transferring the teacher-preferred alternative. We show that aligning the decoding stopping set alone is insufficient, while treating functionally equivalent EOS tokens as a shared semantic stopping action substantially mitigates mismatch-induced length inflation across all three model families. To further understand how termination behavior evolves over training, we study OPD across different K2-Horizon training stages. This stage-wise analysis shows that termination preferences can shift substantially during training, while also revealing a distinct length inflation late in the OPD run that persists beyond termination alignment. Together, these results identify termination mismatch as an important, but not exhaustive, source of OPD length dynamics. We release an implementation incorporating the proposed termination-handling corrections.

Problem

• length inflation
• on-policy distillation
• termination-token mismatch

Innovation

• termination-token mismatch
• on-policy distillation
• EOS tokens
• length inflation
• shared semantic stopping action