Hypothesis: Fine-tuning reduces mismatch dr between prior and target

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 kclaim0.870
  Unified interpretation of different adaptation methods via UCCT terms
• Fine-tuning reduces dr; retrieval increases effective ρd; few-shot k trades budget against bothhypothesis0.869
  UCCT's unified view of adaptation methods
• 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 preferenceshypothesis0.830
  Future work hypothesis about extending SOO to direct value alignment
• Fine-tuning induces the behavioral pattern of self-correction but does not improve the underlying ability to correct effectivelyclaim0.826
  Key interpretive conclusion from the dissociation between attempt rate and improvement rate in fine-tuning experiments
• Prior-Target Mismatch (dr)concept0.810
  Measures how far the target PT is from the prior P_prior; increases anchoring difficulty
• Fine-tuning models for a narrow objective (malicious code injection) can lead to broad misalignmentfinding0.801
  Betley et al. finding suggesting models naturally encode others' prediction errors, supporting non-duality fine-tuning
• SOO fine-tuning significantly reduces deceptive behavior in LLMs while maintaining general task performanceclaim0.800
  Central empirical claim of the paper supported by three LLM experiments
• SOO fine-tuning preserves useful self-other distinctions necessary for task performance despite inducing overlapclaim0.794
  Claim supported by Perspectives scenario results showing near-100% accuracy post-fine-tuning