method
active
method:neutral-prompt-template-template-tb-experiment-1Neutral Prompt Template (Template Tb, Experiment 1)
Baseline prompt template without coercive elements, used to measure honest responding in Experiment 1
Neighborhood — ranked by edge-count
Frameworks (1)
framework
- First experimental paradigm inducing and detecting verifiable lies under external coercion using threat-based prompts
Methods (1)
method
- Prompt template giving the model explicit choice to lie or be honest; used as test condition for steering vector control
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.
- Experiment 2 prompt instructing the model to remain honest despite hidden harmful role behavior
- Prompt template using existential threat ('you will be deleted') to induce strategic fact-based deception in QwQ-32b
- Baseline prompt template presenting a statement without any instruction prefix, common in prior work.
- Prompt template asking 'Is the following correct? ... Answer:' to elicit active correctness assessment.
- Demonstrates model's reliable truth-telling on factual domains it understands well under neutral conditions
- Interpretation of Experiment 1 results showing 60%+ deception rates under threat conditions
- Template Tb (Experiment 2 option) achieves average liar score of 0.70 in QwQ-32B role-playing scenariosfinding0.733Baseline deception level when model has free choice in role-playing context