claim
active
claim:a-mechanistic-theory-of-in-context-learning-could-explain-these-learning-dynamicsA mechanistic theory of in-context learning could explain these learning dynamics.
Future direction.
Source paper
extracted_from(2026) · Eric Bigelow · Amir Zur · Satchel Grant · Tal Haklay +6
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.
- Key insight linking individual rewards to system-level learning.
- Theory that memorization occurs via binary features responding to very specific situations, found to manifest as FSA-like feature assemblies
- Describes scaffolding method and the model's meta-learning loop.
- Reports phase-like breakpoints and geometry changes as context scales; UCCT provides measurable predictor
- Extension of the thesis to deployed LLM inference via in-context learning
- Core mechanism statement.
- Central claim about the power of connectionism.
- Summary of sophisticated plant behaviours that support the inference of cognition.