Classifier-Free Guidance (CFG)

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

• Classifier-free guidance does not decrease type hint rate to deployment levels; activation steering is more effectivefinding0.779
  Comparative result showing steering superiority over CFG as alternative intervention.
• Constitutional Classifiersmethod0.705
  Anthropic's inference-time guardrail filtering outputs violating constitutional rules; proposed for CCAI implementation
• Within-family factual generalization (F0-F2) is consistently strong across all models and prompt settings.finding0.674
  Establishes a reliable baseline for factual truth direction universality within simple factual recall.
• Aragones, Gilboa, Postlewaite & Schmeidler (2005) — Fact-free learningconcept0.672
  Source of fact-free learning concept; associated with insight and computational complexity reduction
• Embedding-based construct classifiers achieve mean accuracy and F1-macro of 95.96% across OCEAN, HEXACO, Dark Tetrad, CMNI, CFNI constructsfinding0.664
  Validates use of lightweight classifiers as replacement for frontier LLM evaluation during alpha sweeps
• Supervised Learning Constitutional AIframework0.663
  The supervised learning stage of CAI where a model critiques and revises its responses, then finetunes on revisions.
• Cosine Similarity Binary Classifiermethod0.652
  Classifier using cosine similarity between activation vectors and steering vectors to detect deception with 89% accuracy