passdrill
AI & LLM Engineering · RAG & Embeddings · Card 017/022 medium

Most RAG systems retrieve passages for every incoming query, even simple ones like 'what is 12 times 4' that the model could answer correctly on its own without any retrieved context, and even in cases where nothing in the index is actually relevant. Self-RAG, introduced by Asai et al. (2023), trains a model to address this by generating special reflection tokens during its own output. What is the specific problem these reflection tokens let the model address?

  1. They let the model retrieve passages in a language other than the one the query was written in, so the retriever can search a multilingual index without a separate translation step
  2. They let the model compress every retrieved passage into a shorter summary before generation, reducing the total number of tokens that must fit inside the context window
  3. They let the model decide on its own, per query, whether retrieval is even needed at all, and separately critique whether a retrieved passage is relevant and whether its own generated output is actually supported by that passage, rather than always retrieving and always trusting whatever was retrieved
  4. They let the model automatically retrain its own retriever component using the current query as a new labeled training example, improving retrieval quality over time
Next card → Shuffle