Retrieval Augmented Generation

Research on integrating external knowledge retrieval with language model generation, covering retrieval strategies, reasoning over retrieved content, and system design tradeoffs. The community studies when and how models should fetch external information versus relying on parametric knowledge.

14 notes (primary) · 1 papers · 1 sub-topics

View as

RAG Variants and Taxonomy

6 notes

Can we defend RAG systems from corpus poisoning without retraining?

Explores whether retrieval-time defenses can catch and block poisoned documents before they reach the generator, without expensive retraining cycles. Matters because corpus updates outpace model retraining in production RAG systems.

Can RAG systems safely learn from their own generated answers?

Explores whether retrieval-augmented generation can feed its outputs back into the corpus without corrupting knowledge with hallucinations. The core problem: how to prevent feedback loops from compounding errors.

Can building a document map first improve retrieval over long texts?

Does constructing a global summary before retrieval help RAG systems connect scattered evidence in long documents the way human readers do? This tests whether understanding document structure improves what gets retrieved.

How can video retrieval handle multiple modalities at different times?

Video RAG systems struggle because the same content appears across visual, audio, and subtitle tracks at offset timestamps. Can temporal awareness in text ranking and frame sampling solve cross-modal misalignment?

Can multimodal knowledge graphs answer questions that flat retrieval cannot?

Can organizing entities and relations from text and images into hierarchical knowledge graphs enable reasoning across entire long documents in ways that chunk-based retrieval fundamentally cannot? Why does hierarchy matter as much as multimodality?

Can describing images in text improve zero-shot recognition?

Explores whether converting visual queries to natural-language descriptions before retrieval outperforms direct visual embedding matching. This matters because visual variation in real-world queries often breaks brittle similarity metrics.