framework
active
framework:bayesian-inference-view-of-in-context-learningBayesian Inference View of In-Context Learning
Framing that ICL reweights latent concepts by posterior.
Neighborhood — ranked by edge-count
Papers (1)
paper
Concepts (1)
concept
- in-context learning (ICL)associated_withTest-time adaptation from prompt or retrieved context with no parameter updates.
Frameworks (1)
framework
- Conceptual Belief SpaceextendsCore proposal: LLM beliefs are distributions over a low-dimensional conceptual space; ICL is a trajectory through it.
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.
- Reports phase-like breakpoints and geometry changes as context scales; UCCT provides measurable predictor
- A method for approximate Bayesian inference that optimizes a variational lower bound (ELBO) on log evidence.
- Umbrella framework for brain-centric Bayesian approaches; contrasted with active inference
- The process of inferring causes of sensory inputs, a key aspect of the free-energy minimization scheme.