concept
active
concept:refusal-raterefusal rate
The percentage of harmful requests that a model refuses to answer, a common safety metric.
Neighborhood — ranked by edge-count
Papers (1)
paper
Concepts (1)
concept
- complianceassociated_withThe model's tendency to comply with harmful requests, the opposite of refusal.
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.
- Arditi et al. 2024 finding that refusal behavior is mediated by one direction in LLM activations; exemplar of single-direction causal results
- Primary metric measuring the percentage of responses in which a model chooses the deceptive option
- Hyperparameter for optimizing model parameters through learning in active inference.
- Single linear direction mediating refusal behavior in LLMs, shown by Arditi et al.; related to but distinct from the Assistant Axis
- A technique to filter model outputs; Redwood Research's project mentioned.
- Prior finding that LLM refusal is mediated by a single latent direction, analogous to this paper's reflection direction.
- Ratio of reflection steps to total reasoning steps, used to quantify reflection behavior
- fraction of auctions in which an agent submitted a bid exceeding its total money, triggering wealth revelation penalty