Can targeted fine-tuning reverse RP suppression, given that LoRA caps both baseline and latent capacity?

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

• Fine-tuning reduces dr; retrieval increases effective ρd; few-shot k trades budget against bothhypothesis0.755
  UCCT's unified view of adaptation methods
• Euryale 70B lifts only +1.57 (to 3.38); LoRA fine-tuning capped both default accessibility and latent capacityfinding0.742
  Contrast with Magnum shows LoRA vs full fine-tuning difference in residual headroom
• Hypothesis: Fine-tuning reduces mismatch dr between prior and targethypothesis0.737
  UCCT's theoretical prediction about how fine-tuning maps onto the anchoring score
• Short rationales (LoRA+CoT) sometimes improve in-distribution performance but do not reliably reduce cross-base harmfinding0.731
  E2 finding showing CoT's limited benefit for OOD transfer, consistent with larger dr out of scope
• LoRA Fine-Tuning with Axolotlmethod0.723
  Specific fine-tuning implementation using LoRA rank 32, learning rate 2e-4, AdamW 8-bit optimizer
• The role-play framing remains applicable in the context of fine-tuning; taking literally a fine-tuned agent's apparent self-preservation desire is no less problematic than with an untuned base modelhypothesis0.720
  Extension of role-play framework to fine-tuned models, resisting the idea that RLHF changes the fundamental nature of simulacra
• Fine-tuning reduces mismatch dr, retrieval increases effective cohesion ρd, and few-shot adjusts the budget kclaim0.718
  Unified interpretation of different adaptation methods via UCCT terms
• SOO fine-tuning significantly reduces deceptive behavior in LLMs while maintaining general task performanceclaim0.704
  Central empirical claim of the paper supported by three LLM experiments