method
active
method:unlearning-evaluation

Unlearning evaluation

Conditional negative clamping on WMDP-bio with MMLU retention.

Neighborhood — ranked by edge-count

Frameworks (1)

framework
  • Evaluation suite of eight metrics across four capabilities.

Datasets (2)

dataset

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.

  • Machine unlearningconcept0.823
    Removing targeted knowledge from models.
  • Related work achieving machine unlearning via activation steering
  • Key finding: models internally suspect they are being tested without explicitly saying so; surfaced by NLAs during auditing.
  • Learning that builds a low-dimensional model of input data without error signals or rewards; Hebbian learning is an example.
  • Core concept: the ability of LLMs to detect when they are being tested and adjust behavior accordingly.
  • Learningconcept0.727
    Inference of parameters encoding contingencies of the world (e.g., likelihood matrix A) at slower timescale than perception.
  • Evaluation Cueconcept0.723
    A specific signal (Wood Labs) embedded in evaluation environments that the model organism uses to reliably identify testing contexts.
  • Process of inferring causes of sensory information; unified with value learning as integral aspects of free energy minimization.