Pith. sign in

REVIEW 3 cited by

Which Examples to Annotate for In-Context Learning? Towards Effective and Efficient Selection

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 2310.20046 v1 pith:VEARAQTW submitted 2023-10-30 cs.CL

classification cs.CL
keywords examplesadaiclimproveslearningsamplingbudgetdiversity-basedefficient
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Large Language Models (LLMs) can adapt to new tasks via in-context learning (ICL). ICL is efficient as it does not require any parameter updates to the trained LLM, but only few annotated examples as input for the LLM. In this work, we investigate an active learning approach for ICL, where there is a limited budget for annotating examples. We propose a model-adaptive optimization-free algorithm, termed AdaICL, which identifies examples that the model is uncertain about, and performs semantic diversity-based example selection. Diversity-based sampling improves overall effectiveness, while uncertainty sampling improves budget efficiency and helps the LLM learn new information. Moreover, AdaICL poses its sampling strategy as a Maximum Coverage problem, that dynamically adapts based on the model's feedback and can be approximately solved via greedy algorithms. Extensive experiments on nine datasets and seven LLMs show that AdaICL improves performance by 4.4% accuracy points over SOTA (7.7% relative improvement), is up to 3x more budget-efficient than performing annotations uniformly at random, while it outperforms SOTA with 2x fewer ICL examples.

Discussion (0). Sign in to comment.

Forward citations

Cited by 3 Pith papers

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

  1. LLMLog: Advanced Log Template Generation via LLM-driven Multi-Round Annotation

    cs.DB 2025-08 conditional novelty 6.0 of 10

    LLMLog uses edit-distance similarity, confidence-weighted annotation selection, and adaptive demonstration coverage to improve LLM-based log template generation.

  2. ConText: Driving In-context Learning for Text Removal and Segmentation

    cs.CV 2025-06 conditional novelty 6.0 of 10

    ConText is the first visual in-context learning model for text removal and segmentation, chaining the two tasks and using self-prompting to reach new state-of-the-art scores.

  3. InSQuAD: In-Context Learning for Efficient Retrieval via Submodular Mutual Information to Enforce Quality and Diversity

    cs.LG 2025-08 conditional novelty 5.0 of 10

    A submodular mutual information framework for selecting and training in-context learning exemplars improves average accuracy on nine benchmarks by about five points over the IDEAL baseline.

Pith tools