Pith. sign in

REVIEW 1 cited by

Positional Information Matters for Invariant In-Context Learning: A Case Study of Simple Function Classes

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 2311.18194 v1 pith:BI4OCL5U submitted 2023-11-30 cs.LG cs.CL

classification cs.LGcs.CL
keywords transformersinvariancedemonstrationsin-contextinputllmspositionalability
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

In-context learning (ICL) refers to the ability of a model to condition on a few in-context demonstrations (input-output examples of the underlying task) to generate the answer for a new query input, without updating parameters. Despite the impressive ICL ability of LLMs, it has also been found that ICL in LLMs is sensitive to input demonstrations and limited to short context lengths. To understand the limitations and principles for successful ICL, we conduct an investigation with ICL linear regression of transformers. We characterize several Out-of-Distribution (OOD) cases for ICL inspired by realistic LLM ICL failures and compare transformers with DeepSet, a simple yet powerful architecture for ICL. Surprisingly, DeepSet outperforms transformers across a variety of distribution shifts, implying that preserving permutation invariance symmetry to input demonstrations is crucial for OOD ICL. The phenomenon specifies a fundamental requirement by ICL, which we termed as ICL invariance. Nevertheless, the positional encodings in LLMs will break ICL invariance. To this end, we further evaluate transformers with identical positional encodings and find preserving ICL invariance in transformers achieves state-of-the-art performance across various ICL distribution shifts

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

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

  1. Rethinking Invariance in In-context Learning

    cs.CL 2025-05 conditional novelty 6.0 of 10

    A leave-one-out attention preprocessing scheme makes in-context learning permutation invariant without sacrificing access to other context examples, improving length and out-of-distribution generalization.

Pith tools