Introspective Diffusion Language Models

TL;DR

This paper introduces Introspective Diffusion Language Models (I-DLMs), which combine diffusion decoding with introspective consistency to match autoregressive model quality and improve efficiency.

Contribution

The paper presents I-DLM, a novel paradigm with an introspective strided decoding algorithm that achieves AR-level quality and higher serving efficiency for diffusion language models.

Findings

I-DLM matches the quality of same-scale autoregressive models.

I-DLM outperforms prior diffusion models on 15 benchmarks.

I-DLM delivers about 3x higher throughput than previous DLMs.

Abstract

Diffusion language models promise parallel generation, yet still lag behind autoregressive (AR) models in quality. We stem this gap to a failure of introspective consistency: AR models agree with their own generations, while DLMs often do not. We define the introspective acceptance rate, which measures whether a model accepts its previously generated tokens. This reveals why AR training has a structural advantage: causal masking and logit shifting implicitly enforce introspective consistency. Motivated by this observation, we introduce Introspective Diffusion Language Model (I-DLM), a paradigm that retains diffusion-style parallel decoding while inheriting the introspective consistency of AR training. I-DLM uses a novel introspective strided decoding (ISD) algorithm, which enables the model to verify previously generated tokens while advancing new ones in the same forward pass. From a systems standpoint, we build I-DLM inference engine on AR-inherited optimizations and further customize it with a stationary-batch scheduler. To the best of our knowledge, I-DLM is the first DLM to match the quality of its same-scale AR counterpart while outperforming prior DLMs in both model quality and practical serving efficiency across 15 benchmarks. It reaches 69.6 on AIME-24 and 45.7 on LiveCodeBench-v6, exceeding LLaDA-2.1-mini (16B) by more than 26 and 15 points, respectively. Beyond quality, I-DLM is designed for the growing demand of large-concurrency serving, delivering about 3x higher throughput than prior state-of-the-art DLMs.