Finetuning Shift

The projection of the activation change induced by finetuning onto a persona vector direction, used to quantify how much a model shifts along a trait

Neighborhood — ranked by edge-count

paper

cosine ≥ 0.65 · no typed edge

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

Fine-tuningconcept0.816
Parameter updates that reduce mismatch dr; another anchoring variant in UCCT.
Fine Tuning and Adaptationconcept0.805
The patient, hand-guided adjustment of shape and dimension to each unique condition in a building; requires materials that make it economical and easy.
Instruction Fine-Tuningconcept0.780
Training procedure that consistently increases HH-intent strength and consistency across model families.
Reinforcement Fine-tuningmethod0.773
OpenAI's internal RL fine-tuning API used to train models with graders rewarding correct or incorrect responses
Fine-Tuning Safetyconcept0.770
The literature documenting how fine-tuning can compromise safety alignment even without malicious intent
fine-tuning (SFT)method0.762
Supervised fine-tuning to adapt model parameters.
Fine-Tuning Threshold Recalibrationmethod0.760
Re-running probabilistic bisection on each fine-tuned checkpoint to normalize first-attempt difficulty
rs-LoRA Finetuningmethod0.760
Low-rank adaptation method used for finetuning models in all experiments; rank 32, alpha 64