concept
active
concept:machine-unlearningMachine unlearning
Removing targeted knowledge from models.
Neighborhood — ranked by edge-count
Papers (1)
paper
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Conditional negative clamping on WMDP-bio with MMLU retention.
- Related work achieving machine unlearning via activation steering
- Learning that builds a low-dimensional model of input data without error signals or rewards; Hebbian learning is an example.
- Process of inferring causes of sensory information; unified with value learning as integral aspects of free energy minimization.
- Emerging field studying psychological properties of LLMs; the paper aims to bridge psychometric methodology with this field
- Emerging multidisciplinary field at interface of artificial life, machine learning, and synthetic bioengineering that provides updated understanding of machines.
- Foundational definitional question motivating the entire paper
- The capability of GPT-3 to learn tasks from few-shot prompts during runtime.