pith. sign in

Estimating Knowledge in Large Language Models Without Generating a Single Token

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.CL 1 cs.LG 1

years

2026 2

representative citing papers

Instructions Shape Production of Language, not Processing

cs.CL · 2026-05-11 · unverdicted · novelty 6.0 · 2 refs

Instructions trigger a production-centered mechanism in language models, with task-specific information stable in input tokens but varying strongly in output tokens and correlating with behavior.

Interpretability Can Be Actionable

cs.LG · 2026-05-11 · conditional · novelty 6.0

Interpretability research should be judged by actionability—the degree to which its insights support concrete decisions and interventions—rather than explanatory power alone.

citing papers explorer

Showing 2 of 2 citing papers.

  • Instructions Shape Production of Language, not Processing cs.CL · 2026-05-11 · unverdicted · none · ref 20 · 2 links

    Instructions trigger a production-centered mechanism in language models, with task-specific information stable in input tokens but varying strongly in output tokens and correlating with behavior.

  • Interpretability Can Be Actionable cs.LG · 2026-05-11 · conditional · none · ref 164

    Interpretability research should be judged by actionability—the degree to which its insights support concrete decisions and interventions—rather than explanatory power alone.