Pith. sign in

REVIEW 2 cited by

An Information-Theoretic Analysis of In-Context Learning

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2401.15530 v1 pith:6REZWYZP submitted 2024-01-28 cs.LG cs.ITmath.IT

classification cs.LGcs.ITmath.IT
keywords errorresultsmeta-learningassumptionscontrivedestablishgeneralin-context
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Previous theoretical results pertaining to meta-learning on sequences build on contrived assumptions and are somewhat convoluted. We introduce new information-theoretic tools that lead to an elegant and very general decomposition of error into three components: irreducible error, meta-learning error, and intra-task error. These tools unify analyses across many meta-learning challenges. To illustrate, we apply them to establish new results about in-context learning with transformers. Our theoretical results characterizes how error decays in both the number of training sequences and sequence lengths. Our results are very general; for example, they avoid contrived mixing time assumptions made by all prior results that establish decay of error with sequence length.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. An Auditable Agent Platform For Automated Molecular Optimisation

    cs.LG 2025-08 conditional novelty 5.0 of 10

    A hierarchical multi-agent LLM platform with recorded provenance improved average predicted binding affinity for AKT1 by 31%, while single-agent runs favored drug-likeness.

  2. Federated In-Context Learning: Iterative Refinement for Improved Answer Quality

    cs.LG 2025-06 conditional novelty 5.0 of 10

    Fed-ICL iteratively refines QA answers via federated in-context learning with only label transmission, showing convergence on a linear attention model and gains on MMLU and TruthfulQA.

Pith tools