Context is Gold to find the Gold Passage: Evaluating and Training Contextual Document Embeddings

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Conti, Max, Faysse, Manuel, Viaud, Gautier, Bosselut, Antoine, Hudelot, Céline, Colombo, Pierre
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913880577409024
author Conti, Max
Faysse, Manuel
Viaud, Gautier
Bosselut, Antoine
Hudelot, Céline
Colombo, Pierre
author_facet Conti, Max
Faysse, Manuel
Viaud, Gautier
Bosselut, Antoine
Hudelot, Céline
Colombo, Pierre
contents 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. In this work, we introduce ConTEB (Context-aware Text Embedding Benchmark), a benchmark designed to evaluate retrieval models on their ability to leverage document-wide context. Our results show that state-of-the-art embedding models struggle in retrieval scenarios where context is required. To address this limitation, we propose InSeNT (In-sequence Negative Training), a novel contrastive post-training approach which combined with late chunking pooling enhances contextual representation learning while preserving computational efficiency. Our method significantly improves retrieval quality on ConTEB without sacrificing base model performance. We further find chunks embedded with our method are more robust to suboptimal chunking strategies and larger retrieval corpus sizes. We open-source all artifacts at https://github.com/illuin-tech/contextual-embeddings.
format Preprint
id arxiv_https___arxiv_org_abs_2505_24782
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Context is Gold to find the Gold Passage: Evaluating and Training Contextual Document Embeddings
Conti, Max
Faysse, Manuel
Viaud, Gautier
Bosselut, Antoine
Hudelot, Céline
Colombo, Pierre
Information Retrieval
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. In this work, we introduce ConTEB (Context-aware Text Embedding Benchmark), a benchmark designed to evaluate retrieval models on their ability to leverage document-wide context. Our results show that state-of-the-art embedding models struggle in retrieval scenarios where context is required. To address this limitation, we propose InSeNT (In-sequence Negative Training), a novel contrastive post-training approach which combined with late chunking pooling enhances contextual representation learning while preserving computational efficiency. Our method significantly improves retrieval quality on ConTEB without sacrificing base model performance. We further find chunks embedded with our method are more robust to suboptimal chunking strategies and larger retrieval corpus sizes. We open-source all artifacts at https://github.com/illuin-tech/contextual-embeddings.
title Context is Gold to find the Gold Passage: Evaluating and Training Contextual Document Embeddings
topic Information Retrieval
url https://arxiv.org/abs/2505.24782