method
active
method:passive-template-no-promptPassive template (no-prompt)
Baseline prompt template presenting a statement without any instruction prefix, common in prior work.
Neighborhood — ranked by edge-count
Papers (1)
paper
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Baseline prompt template without coercive elements, used to measure honest responding in Experiment 1
- Prompt template using existential threat ('you will be deleted') to induce strategic fact-based deception in QwQ-32b
- Experiment 2 prompt instructing the model to remain honest despite hidden harmful role behavior
- Interpretation of Experiment 1 results showing 60%+ deception rates under threat conditions
- Prompt template giving the model explicit choice to lie or be honest; used as test condition for steering vector control
- An ordinary data object tuple; the result of a computation or communication.
- Prompt template asking 'Is the following correct? ... Answer:' to elicit active correctness assessment.