concept
active
concept:refusal-rate

refusal rate

The percentage of harmful requests that a model refuses to answer, a common safety metric.

Neighborhood — ranked by edge-count

Concepts (1)

concept
  • compliance
    associated_with
    The model's tendency to comply with harmful requests, the opposite of refusal.

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

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

  • Refusal directionconcept0.798
    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
  • Learning Rateconcept0.770
    Hyperparameter for optimizing model parameters through learning in active inference.
  • Refusal Vectorconcept0.752
    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.
  • Reflection rateconcept0.736
    Ratio of reflection steps to total reasoning steps, used to quantify reflection behavior
  • overbid ratemethod0.733
    fraction of auctions in which an agent submitted a bid exceeding its total money, triggering wealth revelation penalty