Scilit logo
  • Rankings
  • Search Publications
    Cited-by Search
  • Sources
  • Publishers
  • Scholars
    Top Cited Scholars
  • Organizations
  • Scilit
    About Us
    Advisory Board
    Data Sources
    Career
    Support / Contact
    User Guide
    Publisher User
    Search Function
    Rankings Function
    API Resource
    Scilit Knowledge
    Metrics
    Scilit Recognitions
    Publications Classification
    Media
    News
    Blog
Register
  1. Home
  2. Publications
  3. Unveiling Knowledge Utilization Mechanisms in LLM-based Retrieval-Augmented Generation
  1. Home
  2. Publications
  3. Unveiling Knowledge Utilization Mechanisms in LLM-based Retrieval-Augmented Generation

Unveiling Knowledge Utilization Mechanisms in LLM-based Retrieval-Augmented Generation

Authors:
  • YWYuhao Wang
    Yuhao Wang
  • RRRuiyang Ren
    Ruiyang Ren
  • YWYucheng Wang
    Yucheng Wang
  • WZWayne Xin Zhao
    Wayne Xin Zhao
  • JLJing Liu
    Jing Liu
  • HWHua Wu
    Hua Wu
  • HWHaifeng Wang
    Haifeng Wang

Open Access
Publisher website
Google Scholar
  • 13 July 2025
    • conference paper
    • Published by Association for Computing Machinery (ACM)
    • p. 1262-1271
    • DOI:10.1145/3726302.3730112
Abstract
No abstract available
All Related Versions
  • Version 1, 2025-05-17, ArXiv (Unconfirmed version)

This publication has 9 references indexed in Scilit:

  • Language-Specific Neurons: The Key to Multilingual Capabilities in Large Language Models
    2024
  • When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories
    2023
  • RocketQAv2: A Joint Training Method for Dense Passage Retrieval and Passage Re-ranking
    2021
  • RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answering
    2021
  • Dense Passage Retrieval for Open-Domain Question Answering
    2020
  • Latent Retrieval for Weakly Supervised Open Domain Question Answering
    2019
  • Reading Wikipedia to Answer Open-Domain Questions
    2017
  • TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension
    2017
  • BranchyNet: Fast inference via early exiting from deep neural networks
    2016

Publications with shared reference occurs when two publications share one or more common references. This publication has 9449 Publications with shared reference indexed in Scilit, top 10 records with the most shared references are listed below:

View publications in search results
Cited by 11 articles
Scilit logo

Have questions? Email us at support@scilit.com

© 2026 MDPI (Basel, Switzerland) unless otherwise stated.

MDPI initiatives

  • MDPI Journals
  • MDPI Books
  • Sciforum
  • Proceedings Series
  • Preprints.org
  • SciProfiles
  • Encyclopedia
  • JAMS

Legal

  • Privacy
  • Terms
  • About
  • Contact
  • Disclaimer

Follow us

  • facebook icon
  • x icon
  • linkedin icon

Join us

  • Career

© 2026 MDPI (Basel, Switzerland) unless otherwise stated.