AINeutralarXiv – CS AI · 7h ago6/10
🧠
What Gets Unmasked First? Trajectory Analysis of Diffusion Models for Graph-to-Text Generation
Researchers present the first systematic study of masked diffusion language models (MDLMs) for graph-to-text generation, revealing that these models naturally prioritize entities before relational words and structural tokens. The study identifies a failure mode in supervised fine-tuning that prematurely anchors structural tokens, and proposes lambda-scaled structural decoding to recover performance gains while introducing Graph-LLaDA for improved generalization across datasets.