Long Context vs RAG Quiz

Answers and explanations appear as you take the quiz.

1. Why does the long-context approach usually cost more per query than RAG?
   • Providers charge per input token, and long context sends far more tokens
   • Long-context models require a vector database
   • RAG is always free
   • Long context requires fine-tuning for each question
2. What did the 2023 Lost in the Middle study find?
   • Models ignore the first sentence of every prompt
   • Retrieval always beats long context
   • Performance dropped when relevant information was placed in the middle of long inputs
   • Context windows cannot exceed 4,000 tokens
3. What is a key limitation of needle-in-a-haystack tests?
   • They only work on images
   • They measure simple lookup, not reasoning across many scattered facts
   • They cannot be run on long inputs
   • They measure cost, not accuracy
4. Which situation most clearly favors RAG over long context?
   • A single short policy document queried a few times
   • Summarizing the themes of one novel
   • Comparing two chapters of one report
   • A large, frequently changing corpus with per-user access permissions
5. When using prompt caching with a long corpus, how should the prompt be arranged?
   • Put the question first and the corpus last
   • Shuffle the corpus on each request
   • Put the stable corpus first and the variable question last
   • Split the corpus across separate requests
6. Why does time to first token increase with context length?
   • The model must process every input token before it starts answering
   • Longer prompts are sent over slower networks
   • The model retrieves documents from the internet
   • Output tokens are generated in parallel
7. Which task is long context particularly well suited to?
   • Searching millions of support articles
   • Serving users with different clearance levels
   • Answering from data that changes every hour
   • Summarizing themes across an entire document
8. What does a common hybrid of long context and RAG look like?
   • Using RAG only for images and long context only for text
   • Retrieving relevant documents generously, then including whole documents in a long window
   • Fine-tuning the model on the retrieved chunks
   • Alternating approaches on odd and even days