Retrieval-Augmented Language Modeling

Simlm: Pre-training with representation bottleneck for dense passage retrieval

REPLUG: Retrieval-Augmented Black-Box Language Models

将IT和对比学习损失结合在一起。

Questions Are All You Need to Train a Dense Passage Retriever

Improving Passage Retrieval with Zero-Shot Question Generation

Active Retrieval Augmented Generation

KNOWLEDGE REFINEMENT VIA INTERACTION BETWEEN SEARCH ENGINES AND LARGE LANGUAGE MODELS

Query2doc: Query Expansion with Large Language Models

GENERATE RATHER THAN RETRIEVE: LARGE LANGUAGE MODELS ARE STRONG CONTEXT GENERATORS

In-Context Retrieval-Augmented Language Models