framework
active
framework:icl-as-bayesian-inferenceICL as Bayesian inference
Prior framing of ICL as inference over latent concepts that this paper builds on.
Neighborhood — ranked by edge-count
Papers (1)
paper
Frameworks (2)
framework
- Bayesian ICL (Xie et al. 2022)related_toPrior framework explaining ICL as inference over task structure; UCCT adopts and extends the Bayesian lens
- Closed-form model: ICL accumulates evidence via likelihood, steering shifts priors.
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.
- Views transformers as performing implicit gradient descent; UCCT complements this mechanistic account
- Test-time adaptation from prompt or retrieved context with no parameter updates.
- Views ICL as a form of meta-learning; UCCT sits alongside this account
- A method for approximate Bayesian inference that optimizes a variational lower bound (ELBO) on log evidence.
- The ideal limit of self-supervised learning as modeling the true conditional distribution.