Fine-tuning reduces dr; retrieval increases effective ρd; few-shot k trades budget against both

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

• Fine-tuning reduces mismatch dr, retrieval increases effective cohesion ρd, and few-shot adjusts the budget kclaim0.912
  Unified interpretation of different adaptation methods via UCCT terms
• Hypothesis: Fine-tuning reduces mismatch dr between prior and targethypothesis0.869
  UCCT's theoretical prediction about how fine-tuning maps onto the anchoring score
• SOO fine-tuning significantly reduces deceptive behavior in LLMs while maintaining general task performanceclaim0.799
  Central empirical claim of the paper supported by three LLM experiments
• Fine-tuning induces the behavioral pattern of self-correction but does not improve the underlying ability to correct effectivelyclaim0.790
  Key interpretive conclusion from the dissociation between attempt rate and improvement rate in fine-tuning experiments
• SOO fine-tuning could complement RLHF and Constitutional AI by fostering internal coherence that promotes honest behaviorsclaim0.787
  Integration claim positioning SOO as additive to existing alignment approaches
• Larger LLMs show greater reduction in deceptive behavior after SOO fine-tuningfinding0.783
  Scaling pattern: 78B > 27B > 7B in deception reduction from SOO fine-tuning
• SOO fine-tuning could be extended to align AI representations of its own goals with human user preferences, reducing misalignment by fostering coherence between self-related and other-related preferenceshypothesis0.782
  Future work hypothesis about extending SOO to direct value alignment
• How does light fine-tuning modulate ρd and dr and trade off in-distribution gains against OOD robustness?question0.780
  Third E2 research question examining fine-tuning as anchoring variant with transfer costs