Pith. sign in

REVIEW 1 cited by

RetICL: Sequential Retrieval of In-Context Examples with Reinforcement 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 2305.14502 v2 pith:46RKNOZH submitted 2023-05-23 cs.CL cs.AIcs.LG

RetICL: Sequential Retrieval of In-Context Examples with Reinforcement Learning

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

Recent developments in large pre-trained language models have enabled unprecedented performance on a variety of downstream tasks. Achieving best performance with these models often leverages in-context learning, where a model performs a (possibly new) task given one or more examples. However, recent work has shown that the choice of examples can have a large impact on task performance and that finding an optimal set of examples is non-trivial. While there are many existing methods for selecting in-context examples, they generally score examples independently, ignoring the dependency between them and the order in which they are provided to the model. In this work, we propose Retrieval for In-Context Learning (RetICL), a learnable method for modeling and optimally selecting examples sequentially for in-context learning. We frame the problem of sequential example selection as a Markov decision process and train an example retriever using reinforcement learning. We evaluate RetICL on math word problem solving and scientific question answering tasks and show that it consistently outperforms or matches heuristic and learnable baselines. We also use case studies to show that RetICL implicitly learns representations of problem solving strategies.

discussion (0)

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

Forward citations

Cited by 1 Pith paper

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

  1. UCS: Estimating Unseen Coverage for Improved In-Context Learning

    cs.LG 2026-04 unverdicted novelty 6.0

    UCS estimates the number of unrevealed latent clusters in candidate demonstration sets via Smoothed Good-Turing on embeddings to improve ICL performance by 2-6% when added to baselines.