Source: Bruch, Gai & Ingber 2022: An Analysis of Fusion Functions for Hybrid Retrieval

Paper finding that a tuned convex combination of lexical and semantic scores beats RRF, and that RRF is parameter-sensitive.

Contents
  • What: research paper (ACM TOIS), arXiv:2210.11934
  • Author: Sebastian Bruch, Siyu Gai, Amir Ingber (Pinecone)
  • Date: 2022-10-21 (v2 2023-05-04)
  • Original: arXiv:2210.11934

Summary

Compares ways of fusing lexical (BM25) and dense retrieval scores, focusing on convex combination of normalized scores versus Reciprocal Rank Fusion.

Key claims

  • A convex combination (CC) of lexical and semantic scores outperforms RRF both in-domain and out-of-domain.
  • RRF is sensitive to its parameters, contrary to earlier assumptions.
  • The choice of score normalization has little effect on learning CC.
  • CC has one parameter and can be tuned with a small set of labelled examples from the target domain.

Feeds

Hybrid search

Suggest changes →