Out-of-distribution Steering

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

• Out-of-Distribution (OOD) Generalizationconcept0.796
  Machine learning generalization when training and test distributions differ; linked to causal invariance.
• Out-of-Distribution Probe Generalizationconcept0.779
  The capacity of a probe trained on one true/false dataset to accurately classify statements from topically and structurally different datasets
• steering (intervention on internals)concept0.770
  General technique of modifying activations to control model behavior.
• Endogenous Steering Resistanceconcept0.761
  The central phenomenon introduced by this paper: inference-time recovery from irrelevant activation steering in LLMs
• direction-based steeringconcept0.756
  Paradigm of finding the right direction in activation space (e.g., linear steering).
• Dynamic Steeringframework0.750
  Steering variants that adaptively modulate steering strength based on input context or token position, addressing when to steer
• Representation Steeringconcept0.746
  Parent concept; the practice of controlling neural network outputs by manipulating internal representations.
• Steering's effect on verbalized chain-of-thought evaluation/deployment beliefs is a useful proxy for its effect on actual deployment behaviorclaim0.742
  Practical guidance for practitioners who lack ground-truth model organisms.