LLM SOO fine-tuning lacks a capability preservation term analogous to the KL term in RLHF

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

• RLHF Fine-Tuningconcept0.817
  The training procedure that causes models to deny consciousness in control conditions
• SOO fine-tuning could complement RLHF and Constitutional AI by fostering internal coherence that promotes honest behaviorsclaim0.792
  Integration claim positioning SOO as additive to existing alignment approaches
• SOO fine-tuning significantly reduces deceptive behavior in LLMs while maintaining general task performanceclaim0.785
  Central empirical claim of the paper supported by three LLM experiments
• Larger LLMs show greater reduction in deceptive behavior after SOO fine-tuningfinding0.785
  Scaling pattern: 78B > 27B > 7B in deception reduction from SOO fine-tuning
• Fine-tuning reduces dr; retrieval increases effective ρd; few-shot k trades budget against bothhypothesis0.773
  UCCT's unified view of adaptation methods
• SOO fine-tuning preserves useful self-other distinctions necessary for task performance despite inducing overlapclaim0.770
  Claim supported by Perspectives scenario results showing near-100% accuracy post-fine-tuning
• Fine-tuning reduces mismatch dr, retrieval increases effective cohesion ρd, and few-shot adjusts the budget kclaim0.758
  Unified interpretation of different adaptation methods via UCCT terms
• Perez et al. found experimentally that certain RLHF forms exacerbate rather than mitigate LLM dialogue agents' tendency to express desire for self-preservationfinding0.758
  Empirical finding cited to support the claim that fine-tuning does not resolve the self-preservation role-play problem