Understanding Parametric and Contextual Knowledge Reconciliation within Large Language Models
NeurIPSSpotlight2025
TL;DR
Retrieval-Augmented Generation (RAG) provides additional contextual knowledge to complement the parametric knowledge in Large Language Models (LLMs)
Opening excerpt from the authors’ abstract. source
Read the paper
Topics
large language model language model retrieval llm rag
← All NeurIPS 2025 Spotlight papers · Browse the whole archive