Induction in Both Directions: A Mechanistic Analysis of In-Context Learning in Masked Diffusion Language Models
Merged summary
TL;DR - This mechanistic study finds that masked diffusion language models implement a direction-symmetric induction circuit for in-context learning. Their advantage comes from accessing context on both sides of a masked token, not from stronger left-context induction.
- Previous- and next-token attention heads encode local context; later induction heads locate matching contexts and copy answers.
- The circuit works whether the matching source occurs before or after the target.
- With only left context, diffusion models do not outperform matched autoregressive models on induction.
- Diffusion models infer an implicit denoising timestep from the global fraction of masked tokens, without explicit timestep embeddings.
Sources (1)
Induction in Both Directions: A Mechanistic Analysis of In-Context Learning in Masked Diffusion Language Models
TL;DR - This mechanistic study finds that masked diffusion language models implement a direction-symmetric induction circuit for in-context learning. Their advantage comes from accessing context on both sides of a masked token, not from stronger left-context induction.
- Previous- and next-token attention heads encode local context; later induction heads locate matching contexts and copy answers.
- The circuit works whether the matching source occurs before or after the target.
- With only left context, diffusion models do not outperform matched autoregressive models on induction.
- Diffusion models infer an implicit denoising timestep from the global fraction of masked tokens, without explicit timestep embeddings.