Searcharxiv⌕ Search
Home/Archive/arXiv

arXiv · 2610.29523

pplx-embed-v2-late Technical Report

Markus Krimmel·Louis Milliken·Ekaterina Glazkova·Maximilian Schall·Antoine Chaffin·Sedigheh Eslami·Jonas Golde·Denis Bykov·Claire Beamer·Jeremy Yang·Bo Wang
View original source ↗Read source document ↗Export metadata ↓

Abstract

In this report, we introduce pplx-embed-v2-late, a pair of 0.6B and 9B multilingual and multimodal late-interaction models. Both models achieve state-of-the-art results within their respective size classes across a range of text, image, and visual document retrieval benchmarks. On visual document retrieval tasks, pplx-embed-v2-late-0.6b is competitive with models several times larger than itself. The models are trained via representation distillation from an 18B teacher. Consequently, they share an embedding space that supports asymmetric deployment: documents can be indexed with the 9B model and queried with the low-latency 0.6B model. Both models are available at https://huggingface.co/collections/perplexity-ai/pplx-embed-v2.

Explore related subjects

cs.IRcs.CLcs.LG

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Markus Krimmel, Louis Milliken, Ekaterina Glazkova, Maximilian Schall, Antoine Chaffin, Sedigheh Eslami, Jonas Golde, Denis Bykov, Claire Beamer, Jeremy Yang, Bo Wang. 2026-10-21. pplx-embed-v2-late Technical Report. https://arxiv.org/abs/2610.29523

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

DualView: Adaptive Local-Global Fusion for Multi-Hop Document Reranking

Multi-hop question answering requires aggregating information from multiple documents, a critical capability for knowledge-intensive applications. A fundamental challenge lies in efficiently identifying the minimal relevant document set from retrieved candidates while maintaining high recall. We present an efficient dual-view cascaded reranking framework for multi-hop document reranking. Operating as a lightweight post-retrieval stage over E5-base-v2 candidates, our architecture comprises: (1) a Local Scorer employing stacked cross-attention for fine-grained query-document relevance; and (2) a Global Scorer modeling inter-document dependencies via Transformer-based context aggregation. These views are dynamically fused through an Adaptive Gate conditioned on query semantics. Under the fixed candidate set reranking setting with offline cached embeddings, our model achieves competitive results, particularly outstanding on MuSiQue with 99.4% Top-4 Recall and 97.8% Full Hit accuracy at 4.0 ms latency (249 QPS). It substantially outperforms 600M-parameter cross-encoders (BGE-Large: 92.0% Recall, Jina-v3: 90.1% Recall) while maintaining 5 to 6 times lower latency. Ablation studies validate that both Local and Global views contribute substantially to multi-hop performance.

cs.IR↗
arXiv2026

SIREN (Luring LLMs onto the Rocks): PAIR-Driven Preference Manipulation in Web-RAG Recommenders

This paper investigates the adversarial manipulation of the ranked recommendations produced by web-augmented large language models (LLMs). When an LLM answers a recommendation query by retrieving and reading live webpages, it acts as a recommender, and each retrieved page becomes a potential attack surface. Prior work has examined fabricated products, retrieval poisoning, and rank promotion. However, these studies do not compare how different edits to an already retrieved page change the model's final ranking while the surrounding source set remains unchanged. To address this gap, we propose SIREN, an automated attacker--judge method that adapts the PAIR jailbreaking loop to competitive rank manipulation, with the goal of moving a chosen entity to rank~1 in an LLM-generated recommendation. SIREN retrieves and captures webpages using Anthropic's web tools, then iteratively edits a retrieved source using an interpretable taxonomy of 23 content-poisoning techniques. The custom-RAG replay platform keeps the same sources in the same order, so changes in the model's ranking can be linked to changes in the supplied content rather than to differences in retrieval. Across two production Claude models, SIREN reaches rank~1 in 62 of 124 technique trials nested within eight query--model contexts. The payloads that reached rank~1 were then tested in fresh sessions, where they reproduced the result with a mean success rate of 0.805. Across the evaluated settings, declarative ranking claims and seeded lists were generally more effective than directive-form injections, although the strength of this difference depended on the target model. To the best of our knowledge, this is among the first controlled studies of competitive rank manipulation in production LLMs where the supplied source context is kept fixed.

cs.IR↗
arXiv2026

Hierarchical Exponential-Gaussian Mixtures for Watch-Time Distribution Prediction

Accurate watch-time (WT) prediction is an important requirement for short-video recommendations. Yet WT distributions are near-zero-inflated, long-tailed and multimodal. The recent Exponential-Gaussian Mixture Network (EGMN) models the full conditional WT distribution rather than a single point estimate and achieves state-of-the-art performance. Our large-scale reproduction study reveals that EGMN is vulnerable to variance collapse, component redundancy, and inactive components. We propose a Hierarchical Exponential-Gaussian Mixture (HEGM) model that addresses these failure modes through a hierarchical skip-watch decomposition, structured initialization, removal of the forced Gaussian shift and entropy regularizer and optional KL-based variance regularization for over-parameterized mixtures. Across large-scale industrial and public datasets, under a fixed-backbone head-replacement protocol, HEGM improves ranking accuracy and threshold-event prediction over reproducible lightweight baselines, while maintaining competitive point-estimation accuracy and substantially improving mixture stability and interpretability. A 1.5-month production A/B test confirms statistically significant engagement lifts. Our code and models are publicly released at https://github.com/rw404/HEGM.

cs.IR↗