Pith. sign in

REVIEW 11 cited by

Learning To Retrieve Prompts for 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 2112.08633 v2 pith:F2DU3DAP submitted 2021-12-16 cs.CL cs.LG

Learning To Retrieve Prompts for In-Context Learning

classification cs.CL cs.LG
keywords trainingexampleslearningin-contextlanguagepromptsdataefficient
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

In-context learning is a recent paradigm in natural language understanding, where a large pre-trained language model (LM) observes a test instance and a few training examples as its input, and directly decodes the output without any update to its parameters. However, performance has been shown to strongly depend on the selected training examples (termed prompt). In this work, we propose an efficient method for retrieving prompts for in-context learning using annotated data and a LM. Given an input-output pair, we estimate the probability of the output given the input and a candidate training example as the prompt, and label training examples as positive or negative based on this probability. We then train an efficient dense retriever from this data, which is used to retrieve training examples as prompts at test time. We evaluate our approach on three sequence-to-sequence tasks where language utterances are mapped to meaning representations, and find that it substantially outperforms prior work and multiple baselines across the board.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 11 Pith papers

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

  1. Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?

    cs.CL 2022-02 accept novelty 8.0

    Randomly replacing labels in in-context demonstrations barely hurts performance, showing that label space, input distribution, and sequence format drive in-context learning more than ground-truth labels.

  2. Towards Effective In-context Cross-domain Knowledge Transfer via Domain-invariant-neurons-based Retrieval

    cs.AI 2026-04 unverdicted novelty 7.0

    DIN-Retrieval uses domain-invariant neuron representations to retrieve cross-domain demonstrations, achieving an average 1.8-point gain over state-of-the-art methods on mathematical and logical reasoning tasks.

  3. BCL: Bayesian In-Context Learning Framework for Information Extraction

    cs.CL 2026-06 unverdicted novelty 6.0

    BCL introduces a particle-filtering Bayesian update framework to systematically refine label representations in in-context learning for information extraction, claiming consistent gains over prior methods.

  4. Decompose and Recompose: Reasoning New Skills from Existing Abilities for Cross-Task Robotic Manipulation

    cs.RO 2026-05 unverdicted novelty 6.0

    Decompose and Recompose decomposes seen robotic demonstrations into skill-action alignments and recomposes them via visual-semantic retrieval and planning to enable zero-shot cross-task generalization.

  5. Cognitive Architectures for Language Agents

    cs.AI 2023-09 accept novelty 6.0

    CoALA is a modular cognitive architecture for language agents that organizes memory components, action spaces for internal and external interaction, and a generalized decision-making loop to support more systematic de...

  6. REPLUG: Retrieval-Augmented Black-Box Language Models

    cs.CL 2023-01 conditional novelty 6.0

    REPLUG improves frozen black-box LMs by prepending LM-supervised retrieved documents, delivering 6.3% better language modeling on GPT-3 and 5.1% better five-shot MMLU on Codex.

  7. Neuron-Aware Active Few-Shot Learning for LLMs

    cs.LG 2026-07 unverdicted novelty 5.0

    NeuFS selects active few-shot samples for LLMs by representing samples via neuron activation patterns and applying a dual-criteria strategy of diversity and neuron consensus to identify informative examples.

  8. Rethinking Data Curation in LLM Training: Online Reweighting Offers Better Generalization than Offline Methods

    cs.LG 2026-04 unverdicted novelty 5.0

    ADAPT is an online reweighting framework for LLM training that outperforms offline data selection and mixing methods in cross-benchmark generalization under equal compute.

  9. Reason Analogically via Cross-domain Prior Knowledge: An Empirical Study of Cross-domain Knowledge Transfer for In-Context Learning

    cs.AI 2026-04 unverdicted novelty 5.0

    Cross-domain demonstrations enable conditional positive transfer in in-context learning beyond an example absorption threshold by repairing reasoning structures instead of relying on semantic overlap.

  10. Supplement Generation Training for Enhancing Agentic Task Performance

    cs.LG 2026-04 unverdicted novelty 4.0

    SGT trains a lightweight model to generate task-specific supplemental text that improves performance of a larger frozen LLM on agentic tasks without modifying the large model.

  11. A Comprehensive Overview of Large Language Models

    cs.CL 2023-07 unverdicted novelty 2.0

    A survey paper providing an overview of Large Language Models, their background, and recent advances in the field.