Improving Text Embeddings with Large Language Models: Training

cover
1 Mar 2025

Authors:

(1) Liang Wang, Microsoft Corporation, and Correspondence to (wangliang@microsoft.com);

(2) Nan Yang, Microsoft Corporation, and correspondence to (nanya@microsoft.com);

(3) Xiaolong Huang, Microsoft Corporation;

(4) Linjun Yang, Microsoft Corporation;

(5) Rangan Majumder, Microsoft Corporation;

(6) Furu Wei, Microsoft Corporation and Correspondence to (fuwei@microsoft.com).

Abstract and 1 Introduction

2 Related Work

3 Method

3.1 Synthetic Data Generation

3.2 Training

4 Experiments

4.1 Statistics of the Synthetic Data

4.2 Model Fine-tuning and Evaluation

4.3 Main Results

4.4 Multilingual Retrieval

5 Analysis

5.1 Is Contrastive Pre-training Necessary?

5.2 Extending to Long Text Embeddings and 5.3 Analysis of Training Hyperparameters

6 Conclusion and References

A Implementation Details

B Test Set Contamination Analysis

C Prompts for Synthetic Data Generation

D Instructions for Training and Evaluation

3.2 Training

This paper is available on arxiv under CC0 1.0 DEED license.