RARe: Retrieval Augmented Retrieval with In-Context Examples

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tejaswi, Atula, Lee, Yoonsang, Sanghavi, Sujay, Choi, Eunsol
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917255590182912
author Tejaswi, Atula
Lee, Yoonsang
Sanghavi, Sujay
Choi, Eunsol
author_facet Tejaswi, Atula
Lee, Yoonsang
Sanghavi, Sujay
Choi, Eunsol
contents While in-context learning is well-studied with decoder-only language models (LLMs), its utility for encoder-only models remains underexplored. We study in-context learning for encoder-only models for text retrieval tasks. Can incorporating in-context examples (query-document pairs) to the target query enhance retriever performance? Our approach, RARe, finetunes a pre-trained model with in-context examples whose query is semantically similar to the target query. This approach achieves performance gains of up to +2.72% nDCG across open-domain retrieval datasets (BeIR, RAR-b) compared to using the target query only as an input. In particular, we find RARe exhibits stronger out-of-domain generalization compared to models using queries without in-context examples, similar to what is seen for in-context learning in LLMs. We further provide analysis on the design choices of in-context example augmentation for retrievers and lay the foundation for future work.
format Preprint
id arxiv_https___arxiv_org_abs_2410_20088
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle RARe: Retrieval Augmented Retrieval with In-Context Examples
Tejaswi, Atula
Lee, Yoonsang
Sanghavi, Sujay
Choi, Eunsol
Computation and Language
Artificial Intelligence
Information Retrieval
While in-context learning is well-studied with decoder-only language models (LLMs), its utility for encoder-only models remains underexplored. We study in-context learning for encoder-only models for text retrieval tasks. Can incorporating in-context examples (query-document pairs) to the target query enhance retriever performance? Our approach, RARe, finetunes a pre-trained model with in-context examples whose query is semantically similar to the target query. This approach achieves performance gains of up to +2.72% nDCG across open-domain retrieval datasets (BeIR, RAR-b) compared to using the target query only as an input. In particular, we find RARe exhibits stronger out-of-domain generalization compared to models using queries without in-context examples, similar to what is seen for in-context learning in LLMs. We further provide analysis on the design choices of in-context example augmentation for retrievers and lay the foundation for future work.
title RARe: Retrieval Augmented Retrieval with In-Context Examples
topic Computation and Language
Artificial Intelligence
Information Retrieval
url https://arxiv.org/abs/2410.20088