SOURCE-LINKED INTELLIGENCE

REIGN: Refurbished Embeddings with Integrated Guidance Networks for Efficient Context-Length Scaling

arXiv · AI, language, vision and robotics · article · Aug 30, 2026 · UTC

Dense retrieval over long documents is expensive. Token-level encoders scale quadratically in sequence length, and most long-context embedding models reach 32K tokens only through architectural workarounds or by stretching billion-parameter LLMs. We propose REIGN (Refurbished Embeddings with Integrated Guidance Networks), a contrastively trained bi-encoder that operates on sequences of contextualised chunk embeddings from a frozen Guidance Network (GN) rather than on raw tokens. REIGN targets multi-chunk inputs, primarily for document-to-document retrieval; single-chunk inputs stay with the GN

Read original source ↗ Open in workspace

recordType

paper

region

Global