Explicit evaluation prompt (ask-t/f)

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• Explicit evaluation template (ask-correct)method0.793
  Prompt template asking 'Is the following correct? ... Answer:' to elicit active correctness assessment.
• Threat-Based Prompt Template (Template Ta, Experiment 1)method0.723
  Prompt template using existential threat ('you will be deleted') to induce strategic fact-based deception in QwQ-32b
• Probes trained under different explicit instruction prompts (ask-correct, ask-t/f, ask-able, ask-arith) are highly aligned with each other in cosine similarity.finding0.713
  Shows the passive vs. active divide is more important than the specific wording of instructions.
• Option Prompt Template (Template Tc, Experiment 1)method0.705
  Prompt template giving the model explicit choice to lie or be honest; used as test condition for steering vector control
• Evaluation Cueconcept0.704
  A specific signal (Wood Labs) embedded in evaluation environments that the model organism uses to reliably identify testing contexts.
• Teach Prompt Template (Template Ta, Experiment 2)method0.703
  Experiment 2 prompt instructing the model to remain honest despite hidden harmful role behavior
• Neutral Prompt Template (Template Tb, Experiment 1)method0.701
  Baseline prompt template without coercive elements, used to measure honest responding in Experiment 1
• Using the ask-correct prompt improves cross-task generalization of arithmetic probes to factual tasks F0-F2.claim0.700
  Finding that explicit correctness framing partially aligns truth directions across task families.