Skip to content
Sagan

Paper

Instructions shape Production of Language, not Processing

Unreadunread

AI summary

The authors show that instructions in language models primarily affect how output tokens are produced rather than how input tokens are processed. Using layer-by-layer probing across five tasks, they find that task-specific information in the input stays mostly stable regardless of instructions, while the same information in output tokens varies dramatically and tracks actual behavior. Attention interventions confirm this causally: blocking instruction influence to all tokens hurts performance, but blocking it only to input tokens barely matters.

Main takeaways:

  • Instructions shape what happens during output generation, not during input understanding—an asymmetry between "processing" and "production" stages
  • Task information encoded in output tokens correlates strongly with behavior; the same information in input tokens correlates weakly
  • Blocking instruction attention flow to output tokens tanks performance; blocking it only to input tokens has minimal effect
  • The effect becomes sharper with model scale and instruction-tuning, both of which disproportionately amplify the production stage
  • Suggests measuring model internals by token position (input vs output) reveals more than treating all positions the same