Diffutron: A Masked Diffusion Language Model for Turkish Language
This work addresses the problem of non-autoregressive text generation for Turkish, a morphologically rich language, but is incremental as it adapts existing methods to a new domain.
The paper tackled the limited application of masked diffusion language models to morphologically rich languages by introducing Diffutron, a model designed for Turkish, which achieved competitive performance on benchmarks compared to larger baselines despite its compact size.
Masked Diffusion Language Models (MDLMs) have emerged as a compelling non-autoregressive alternative to standard large language models; however, their application to morphologically rich languages remains limited. In this paper, we introduce $\textit{Diffutron}$, a masked diffusion language model specifically designed for Turkish. Our approach leverages a resource-efficient training pipeline, starting with LoRA-based continual pre-training of a multilingual encoder on a large-scale corpus. To enable generative capabilities, we employ a progressive instruction-tuning strategy, sequentially adapting the model on general and task-specific instruction sets. Experimental results across comprehensive benchmarks demonstrate that, despite its compact size, our model achieves competitive performance compared to existing multi-billion-parameter baselines. These findings validate the effectiveness of masked diffusion modeling combined with multi-stage tuning for non-autoregressive text generation in Turkish.