Pith. sign in

REVIEW 7 cited by

Self-Generated In-Context Learning: Leveraging Auto-regressive Language Models as a Demonstration Generator

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 2206.08082 v1 pith:ZKGOT6CK submitted 2022-06-16 cs.CL

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

Large-scale pre-trained language models (PLMs) are well-known for being capable of solving a task simply by conditioning a few input-label pairs dubbed demonstrations on a prompt without being explicitly tuned for the desired downstream task. Such a process (i.e., in-context learning), however, naturally leads to high reliance on the demonstrations which are usually selected from external datasets. In this paper, we propose self-generated in-context learning (SG-ICL), which generates demonstrations for in-context learning from PLM itself to minimize the reliance on the external demonstration. We conduct experiments on four different text classification tasks and show SG-ICL significantly outperforms zero-shot learning and is generally worth approximately 0.6 gold training samples. Moreover, our generated demonstrations show more consistent performance with low variance compared to randomly selected demonstrations from the training dataset.

Discussion (0). Sign in to comment.

Forward citations

Cited by 7 Pith papers

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

  1. Which Prompting Technique Should I Use? An Empirical Investigation of Prompting Techniques for Software Engineering Tasks

    cs.SE 2025-06 conditional novelty 6.0 of 10

    Across ten software engineering tasks and four LLMs, no prompting technique wins consistently; ES-KNN is best on many tasks, some techniques underperform the baseline, and USC is best for code QA and code generation.

  2. Exploring In-context Example Generation for Machine Translation

    cs.CL 2025-05 conditional novelty 6.0 of 10

    DAT generates query-specific in-context translation examples using only an LLM, improving English-to-low-resource translation over zero-shot in most tested languages.

  3. CrossICL: Cross-Task In-Context Learning via Unsupervised Demonstration Transfer

    cs.CL 2025-05 conditional novelty 6.0 of 10

    CrossICL reuses demonstrations from similar source tasks, rewriting them into the target task's format, and improves zero-shot ICL on Super-NI without target-task annotations.

  4. Learning to Select Visual In-Context Demonstrations

    cs.LG 2026-03 reject novelty 5.0 of 10

    A Dueling-DQN agent selects visual in-context demonstrations and outperforms kNN retrieval on objective regression benchmarks but not on subjective preference tasks, per the paper's main table.

  5. DICE: Dynamic In-Context Example Selection in LLM Agents via Efficient Knowledge Transfer

    cs.AI 2025-07 conditional novelty 5.0 of 10

    DICE dynamically retrieves the most relevant in-context demonstrations at each agent step, and in this preprint it raises exact-match and success-rate scores on HotpotQA, ALFWorld, and Webshop across ReAct, Reflexion,...

  6. Unveiling Effective In-Context Configurations for Image Captioning: An External & Internal Analysis

    cs.CL 2025-07 conditional novelty 5.0 of 10

    For Flamingo-style models, increasing the number of in-context examples improves language coherence but degrades visual-text alignment, and similarity-based image retrieval inflates CIDEr scores by encouraging caption...

  7. Learning-to-Context Slope: Evaluating In-Context Learning Effectiveness Beyond Performance Illusions

    cs.CL 2025-06 conditional novelty 5.0 of 10

    LCS, a slope between learning gain and contextual relevance, is proposed and shown to correlate with ICL performance gains, with a suggested threshold of 0.2 for effective in-context learning.

Pith tools