Maximum Marginal Relevance Quiz

Answers and explanations appear as you take the quiz.

1. What is the primary problem MMR is designed to solve?
   • Slow query latency in large databases
   • Incorrect spelling in user queries
   • Redundant, near-duplicate results from pure relevance ranking
   • Lack of training data for embeddings
2. In the MMR formula, what does a lambda value close to 1 emphasize?
   • Pure relevance to the query
   • Maximum diversity among results
   • Equal weighting of all candidates
   • Random selection
3. How does MMR select its results?
   • All at once by sorting a single score
   • Randomly with a fixed seed
   • By alphabetical order of documents
   • Greedily, one at a time, comparing to already-selected items
4. How can an embedding-based MMR implementation measure query relevance and document redundancy?
   • Using only a document's filename length
   • Using a similarity measure such as cosine, without MMR requiring that one measure universally
   • Using a mandatory audio-transcription score for all text
   • Using no relevance or inter-document comparison at all
5. Why is MMR especially useful in retrieval-augmented generation (RAG)?
   • It supplies complementary, non-redundant evidence chunks
   • It compresses the model's weights
   • It fine-tunes the language model automatically
   • It encrypts retrieved documents
6. If MMR caches each candidate's maximum redundancy and updates it against each new selection, roughly how many similarities are needed for k picks from n candidates?
   • Always constant time independent of k and n
   • Exactly n factorial for every implementation
   • About k times n, ignoring vector dimension and initial setup
   • No document comparisons after the first query score
7. With lambda equal to 0.5, relevance 0.8, and maximum selected-item similarity 0.9, what is a candidate's MMR scoring term?
   • 0.85, from averaging the two similarities
   • Minus 0.05, from 0.5 times 0.8 minus 0.5 times 0.9
   • 0.72, from multiplying relevance and redundancy
   • 1.7, from adding the two similarities
8. Can an MMR reranker select a relevant document that the upstream retrieval candidate pool omitted?
   • Yes; diversity scoring invents missing source documents
   • Yes; a lower lambda automatically searches the whole corpus
   • Yes; reranking changes the document's original publication date
   • No; it chooses among the supplied candidates unless the upstream pool is expanded