concept
active
concept:adversarial-interactionadversarial interaction
Competitive multi-agent setting with conflicting incentives and direct opposition via bidding and bluffing.
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.
- Technique used in VPD to enforce mechanistic faithfulness of parameter decompositions.
- Eight instruction variants appended to prompts to attempt to break superficial role-play and test depth of character
- Risk that multiple truth directions enable attacks that shift outputs without triggering the primary truth direction
- Optimization-based jailbreak method appending strings to prompts to elicit harmful outputs.
- A sequence of context-response pairs where each context includes the preceding sequence, formalising LM dialogue dynamics.
- Procedure in VPD that actively searches for combinations that break the prediction of which subcomponents are unimportant, stress-testing the decomposition.