Why Non-Causal Training Is Data-Inefficient — And What DeepSeek V4.1 Could Have Done

ThePremiseOfIt · x · 2026-09-11

ThePremiseOfIt explains why non-causal training is so difficult: autoregression converts each length-T context into T input-output pairs, so training scales with total tokens; non-causal training yields only one pair per context, far less efficient. That's a key reason diffusion models are data-inefficient, and why block diffusion gained traction (T//n pairs at the cost of limited generation length n).

He also speculates that DeepSeek V4.1's architecture could have used a non-causal encoder + causal decoder trained only on decoded tokens, potentially making it a much stronger reasoner. He notes overcoming this data-efficiency gap is part of what his company Premise works on.

Related event: Debate Flares Over Autoregressive vs Diffusion Training Efficiency(4 posts)→

Original post →

More from Research

Research channel →