Exploring the Role of Diversity in Example Selection for In-Context Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kapuriya, Janak, Kaushik, Manit, Ganguly, Debasis, Bhatia, Sumit
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915275176148992
author Kapuriya, Janak
Kaushik, Manit
Ganguly, Debasis
Bhatia, Sumit
author_facet Kapuriya, Janak
Kaushik, Manit
Ganguly, Debasis
Bhatia, Sumit
contents In-Context Learning (ICL) has gained prominence due to its ability to perform tasks without requiring extensive training data and its robustness to noisy labels. A typical ICL workflow involves selecting localized examples relevant to a given input using sparse or dense embedding-based similarity functions. However, relying solely on similarity-based selection may introduce topical biases in the retrieved contexts, potentially leading to suboptimal downstream performance. We posit that reranking the retrieved context to enhance topical diversity can improve downstream task performance. To achieve this, we leverage maximum marginal relevance (MMR) which balances topical similarity with inter-example diversity. Our experimental results demonstrate that diversifying the selected examples leads to consistent improvements in downstream performance across various context sizes and similarity functions. The implementation of our approach is made available at https://github.com/janak11111/Diverse-ICL.
format Preprint
id arxiv_https___arxiv_org_abs_2505_01842
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Exploring the Role of Diversity in Example Selection for In-Context Learning
Kapuriya, Janak
Kaushik, Manit
Ganguly, Debasis
Bhatia, Sumit
Information Retrieval
In-Context Learning (ICL) has gained prominence due to its ability to perform tasks without requiring extensive training data and its robustness to noisy labels. A typical ICL workflow involves selecting localized examples relevant to a given input using sparse or dense embedding-based similarity functions. However, relying solely on similarity-based selection may introduce topical biases in the retrieved contexts, potentially leading to suboptimal downstream performance. We posit that reranking the retrieved context to enhance topical diversity can improve downstream task performance. To achieve this, we leverage maximum marginal relevance (MMR) which balances topical similarity with inter-example diversity. Our experimental results demonstrate that diversifying the selected examples leads to consistent improvements in downstream performance across various context sizes and similarity functions. The implementation of our approach is made available at https://github.com/janak11111/Diverse-ICL.
title Exploring the Role of Diversity in Example Selection for In-Context Learning
topic Information Retrieval
url https://arxiv.org/abs/2505.01842