xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Token

Mar-22-2026, 10:37:29 GMT–Neural Information Processing Systems

This paper introduces xRAG, an innovative context compression method tailored for retrieval-augmented generation.

large language model, machine learning, natural language, (10 more...)

Neural Information Processing Systems

Mar-22-2026, 10:37:29 GMT

Conferences Web Page

Technology:
- Information Technology > Artificial Intelligence
  - Natural Language
    - Large Language Model (0.33)
    - Chatbot (0.33)
  - Machine Learning > Neural Networks
    - Deep Learning (0.33)