Enhancement steering consistently underperforms compared to directly providing explicit reflection instructions across all tested conditions

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

• Inhibition steering produces larger accuracy drops than enhancement steering produces accuracy gains, across all models and datasets testedfinding0.816
  Key asymmetry finding: suppressing reflection is easier than inducing it.
• Steering vectors enable systematic discovery of reflection-inducing instructions beyond trial-and-error prompt design.claim0.784
  Core applied contribution claim, supported by top-k accuracy comparisons.
• Steering vectors discover effective triggers such as 'However' and 'Otherwise', consistent with prior reported reflection datasetsfinding0.780
  Validates that steering vectors capture reflection semantics by finding tokens reported in related work.
• Activation steering interventions generally succeed in guiding performance toward the desired direction (enhancement increases accuracy, inhibition decreases accuracy) compared to unsteered baselinefinding0.773
  Core validation that identified latent directions correspond to meaningful control over reflective behavior.
• Stepwise steering achieves over 5% accuracy improvement compared to all-token intervention at similar token budgetfinding0.772
  Key result demonstrating advantage of stepwise over all-token steering strategy
• Steering affects type hint writing by modifying the model's belief about whether it is being evaluated, not by directly encoding type hint informationclaim0.766
  Mechanism claim supported by transcript analysis and the fact that the steering vector was extracted from a model that never writes type hints.
• The ease of suppressing reflection via activation steering raises security risks, as malicious actors could exploit reflection inhibition to bypass model safeguards.claim0.765
  Applied security implication derived from the asymmetry finding.
• Steering vectors to reduce eval awareness can inadvertently insert alternative user personasclaim0.765
  Caution: interventions targeting eval awareness may have unintended side effects.