method
active
method:lora-sft

LoRA SFT

Light fine-tuning method used in E2 to reduce mismatch dr.

Neighborhood — ranked by edge-count

Concepts (2)

concept
  • Fine-tuning
    implements
    Parameter updates that reduce mismatch dr; another anchoring variant in UCCT.
  • Target Pattern Cohesion (ρd)
    associated_with
    Measures how tightly the target pattern PT clusters in representation space; one of three components of S

Methods (1)

method

Related by similarity (8)

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.

  • LoRA adapterconcept0.738
    Fine-tuning technique that can effectively add a constant vector to the residual stream, equivalent to steering along a persona direction
  • LoRA Adaptersmethod0.730
    Parameter-efficient fine-tuning method used in both distillation and introspection stages
  • fine-tuning (SFT)method0.717
    Supervised fine-tuning to adapt model parameters.
  • rs-LoRA Finetuningmethod0.716
    Low-rank adaptation method used for finetuning models in all experiments; rank 32, alpha 64
  • LoRA Fine-Tuningmethod0.716
    Adaptation method used via Tinker API for DeepSeek-V3.1 and Qwen3-235B fine-tuning with rank 32
  • Supervised Fine-tuning (SFT)method0.707
    Full fine-tuning of GPT-4o on synthetic datasets; primary method for inducing emergent misalignment
  • LoRA+CoTmethod0.704
    Fine-tuning with chain-of-thought rationales aiming to reduce dr via procedural alignment.
  • LoRA (Low-Rank Adaptation)method0.698
    Parameter-efficient fine-tuning method used for both SDF and expert iteration stages.