Unverified50% confidenceFactExact time
INLP (Iterative Nullspace Projection) is a linear method for removing a specific attribute from a representation, eliminating that direction of information by training a linear classifier and projecting the representation onto its nullspace; its limitation is that it can only remove linearly separable attributes.
1
Sources
50%
Confidence
Long-term
Relevance
10/23/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedZero-shot transfer refers to a model performing inference directly on an unseen data distribution without using any target-domain labels or fine-tuning, and its performance ceiling is limited by the coverage of the source-domain prior.59% similarUnverifiedINLA (Integrated Nested Laplace Approximation) is an approximate inference method for Bayesian hierarchical models that replaces MCMC sampling with Laplace approximations, yielding approximations to posterior distributions at a much lower computational cost.58% similarUnverifiedThe core principle of Abliteration is to identify the refusal direction in the model's residual stream and eliminate it via orthogonal projection from the weight matrices.58% similarUnverifiedA project implementing linear regression from scratch using NumPy connects calculus, linear algebra, and programming, helping one understand the effect of gradient descent and learning rate on convergence.57% similarVerifiedA linear probe is a simple linear classifier trained on model activations, used to detect whether specific behaviors or concepts exist inside the model.55% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1088124API
curl https://kongchang.com/api/v1/knowledge/claims/1088124MCP
get_claim(id=1088124)