ARTFEED — Contemporary Art Intelligence

DIVE: New Embedding Compression Method for LLMs

ai-technology · 2026-05-22

A new method called DIVE (Dimensionality reduction with Implicit View Ensembles) addresses overfitting in embedding compression for large language models. Proposed in arXiv:2605.20689, DIVE uses a self-limiting hinge-based triplet loss and head-wise NT-Xent contrastive loss to reduce dimensionality without degrading retrieval performance, unlike prior methods such as Matryoshka-Adaptor, Search-Adaptor, and SMEC. The approach bounds perturbations to pretrained embeddings, improving efficiency for vector search systems.

Key facts

  • DIVE is a compression adapter for LLM embeddings.
  • It uses self-limiting hinge-based triplet loss.
  • It uses head-wise NT-Xent contrastive loss.
  • Prior methods: Matryoshka-Adaptor, Search-Adaptor, SMEC.
  • Overfitting occurs when labeled data is scarce.
  • DIVE maintains retrieval performance above frozen baseline.
  • Method reduces storage and computational costs.
  • Paper appears on arXiv with ID 2605.20689.

Entities

Institutions

  • arXiv

Sources