Training-Free Length Discovery for Diffusion Language Model Infilling

Hengchang Liu, Zhao Yang, Bing Su

Keywords: Diffusion Language Models, Generative Infilling, Adaptive Length Control, Training-Free Generation

Abstract: Diffusion language models (DLMs) provide a bidirectional generation framework naturally suited for infilling, yet their performance is constrained by the pre-specified infilling length. In this paper, we reveal that DLMs possess an inherent ability to discover the correct infilling length. We identify two key statistical phenomena in the first-step denoising confidence: a local *Oracle Peak* that emerges near the ground-truth length and a systematic *Length Bias* that often obscures this signal. By leveraging this signal and calibrating the bias, our training-free method **CAL** (**C**alibrated **A**daptive **L**ength) enables DLMs to approximate the optimal length through an efficient search before formal decoding. Empirical evaluations demonstrate that CAL improves Pass@1 by up to 47.7\% over fixed-length baselines and 40.5\% over chat-based adaptive methods in code infilling, while boosting BLEU-2 and ROUGE-L by up to 8.5\% and 9.9\% in text infilling. These results demonstrate that CAL paves the way for robust DLM infilling without requiring any specialized training.

Submission Number: 14