Context is Gold to find the Gold Passage: Evaluating and Training Contextual Document Embeddings
Main:8 Pages
6 Figures
Bibliography:3 Pages
5 Tables
Appendix:3 Pages
Abstract
A limitation of modern document retrieval embedding methods is that they typically encode passages (chunks) from the same documents independently, often overlooking crucial contextual information from the rest of the document that could greatly improve individual chunk representations.
View on arXiv@article{conti2025_2505.24782,
title={ Context is Gold to find the Gold Passage: Evaluating and Training Contextual Document Embeddings },
author={ Max Conti and Manuel Faysse and Gautier Viaud and Antoine Bosselut and Céline Hudelot and Pierre Colombo },
journal={arXiv preprint arXiv:2505.24782},
year={ 2025 }
}Comments on this paper