Context Regeneration Filters Irrelevance

System 2 Attention (S2A) addresses a fundamental problem: soft attention in Transformers incorporates everything in context, including irrelevant or misleading information.

The solution: regenerate the input context using the model’s own reasoning, keeping only relevant portions.

Two-step process:

  1. Ask the model to extract and rewrite only the relevant context
  2. Generate the response using this filtered context

Results:

  • Factual QA accuracy: 80.3%
  • Long-form generation objectivity: 3.82/5.0

The pattern generalizes: when context includes noise that might mislead attention, explicit filtering (even if imperfect) beats hoping attention learns to ignore it.

This is preprocessing as a prompting strategy, shaping the input before reasoning begins.

Related: 05-molecule—attention-mechanism-concept