COS-Mix: Cosine Similarity and Distance Fusion for Improved Information Retrieval

TL;DR

This paper introduces COS-Mix, a hybrid retrieval method combining cosine similarity and cosine distance to enhance information retrieval accuracy, especially for sparse data, by capturing both similarity and dissimilarity in high-dimensional vector spaces.

Contribution

The paper presents a novel hybrid retrieval strategy that fuses cosine similarity and cosine distance measures, improving retrieval performance over traditional methods.

Findings

Enhanced retrieval accuracy demonstrated on proprietary datasets.

Hybrid approach captures both similarity and dissimilarity effectively.

Improved understanding of semantic relationships in information retrieval.

Abstract

This study proposes a novel hybrid retrieval strategy for Retrieval-Augmented Generation (RAG) that integrates cosine similarity and cosine distance measures to improve retrieval performance, particularly for sparse data. The traditional cosine similarity measure is widely used to capture the similarity between vectors in high-dimensional spaces. However, it has been shown that this measure can yield arbitrary results in certain scenarios. To address this limitation, we incorporate cosine distance measures to provide a complementary perspective by quantifying the dissimilarity between vectors. Our approach is experimented on proprietary data, unlike recent publications that have used open-source datasets. The proposed method demonstrates enhanced retrieval performance and provides a more comprehensive understanding of the semantic relationships between documents or items. This hybrid strategy offers a promising solution for efficiently and accurately retrieving relevant information in knowledge-intensive applications, leveraging techniques such as BM25 (sparse) retrieval , vector (Dense) retrieval, and cosine distance based retrieval to facilitate efficient information retrieval.