Diffusion-Pretrained Dense and Contextual Embeddings

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Eslami, Sedigheh, Gaiduk, Maksim, Krimmel, Markus, Milliken, Louis, Wang, Bo, Bykov, Denis
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911446052372480
author Eslami, Sedigheh
Gaiduk, Maksim
Krimmel, Markus
Milliken, Louis
Wang, Bo
Bykov, Denis
author_facet Eslami, Sedigheh
Gaiduk, Maksim
Krimmel, Markus
Milliken, Louis
Wang, Bo
Bykov, Denis
contents In this report, we introduce pplx-embed, a family of multilingual embedding models that employ multi-stage contrastive learning on a diffusion-pretrained language model backbone for web-scale retrieval. By leveraging bidirectional attention through diffusion-based pretraining, our models capture comprehensive bidirectional context within passages, enabling the use of mean pooling and a late chunking strategy to better preserve global context across long documents. We release two model types: pplx-embed-v1 for standard retrieval, and pplx-embed-context-v1 for contextualized embeddings that incorporate global document context into passage representations. pplx-embed-v1 achieves competitive performance on the MTEB(Multilingual, v2), MTEB(Code), MIRACL, BERGEN, and ToolRet retrieval benchmarks, while pplx-embed-context-v1 sets new records on the ConTEB benchmark. Beyond public benchmarks, pplx-embed-v1 demonstrates strong performance on our internal evaluation suite, focusing on real-world, large-scale search scenarios constructed from 1B production web pages. These results validate the models' effectiveness in production environments where retrieval quality and efficiency are critical at scale.
format Preprint
id arxiv_https___arxiv_org_abs_2602_11151
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Diffusion-Pretrained Dense and Contextual Embeddings
Eslami, Sedigheh
Gaiduk, Maksim
Krimmel, Markus
Milliken, Louis
Wang, Bo
Bykov, Denis
Machine Learning
Computation and Language
Information Retrieval
In this report, we introduce pplx-embed, a family of multilingual embedding models that employ multi-stage contrastive learning on a diffusion-pretrained language model backbone for web-scale retrieval. By leveraging bidirectional attention through diffusion-based pretraining, our models capture comprehensive bidirectional context within passages, enabling the use of mean pooling and a late chunking strategy to better preserve global context across long documents. We release two model types: pplx-embed-v1 for standard retrieval, and pplx-embed-context-v1 for contextualized embeddings that incorporate global document context into passage representations. pplx-embed-v1 achieves competitive performance on the MTEB(Multilingual, v2), MTEB(Code), MIRACL, BERGEN, and ToolRet retrieval benchmarks, while pplx-embed-context-v1 sets new records on the ConTEB benchmark. Beyond public benchmarks, pplx-embed-v1 demonstrates strong performance on our internal evaluation suite, focusing on real-world, large-scale search scenarios constructed from 1B production web pages. These results validate the models' effectiveness in production environments where retrieval quality and efficiency are critical at scale.
title Diffusion-Pretrained Dense and Contextual Embeddings
topic Machine Learning
Computation and Language
Information Retrieval
url https://arxiv.org/abs/2602.11151