Query Rewriting and Multi-Query Retrieval Quiz

Answers and explanations appear as you take the quiz.

1. Why is query rewriting especially important in multi-turn chat?
   • Follow-up messages often depend on earlier context and are meaningless as standalone searches
   • Chat models cannot generate text
   • Vector databases reject questions
   • Longer queries are always faster
2. Which technique splits a comparison question into separate searches for each item being compared?
   • HyDE
   • Reciprocal rank fusion
   • Decomposition
   • Prompt caching
3. What does step-back prompting do?
   • Deletes the user's query
   • Retrieves only the most recent documents
   • Reverses the order of search results
   • Asks a more general question first to retrieve background principles
4. In reciprocal rank fusion, how is a document's score calculated?
   • The average of raw similarity scores
   • The sum of 1/(k + rank) across result lists
   • The number of words it shares with the query
   • Its rank in the first list only
5. Why is RRF convenient for merging vector search and BM25 results?
   • It relies on ranks, so scores on different scales need no normalization
   • It requires identical scoring functions
   • It only works with a single list
   • It retrains the embedding model
6. What does HyDE embed instead of the user's question?
   • The document title
   • A random sample of chunks
   • A hypothetical answer written by the model
   • The user's conversation history
7. What is a recommended safeguard against intent drift in multi-query retrieval?
   • Generate at least twenty variants
   • Remove all named entities from variants
   • Skip deduplication
   • Include the original query as one of the variants and preserve entities and dates
8. Which is a real drawback of generating many query variants?
   • It makes RRF impossible
   • It adds latency and cost and can pull in irrelevant documents
   • It prevents reranking
   • It always lowers recall to zero