Mid-level interview question
When can fusion make retrieval worse?
Model answer
When one retriever returns noise for a class of queries. On the course's six queries, BM25 matched a single common word (“every”, “phone”) in unrelated articles, those spurious matches got votes, and fusion ranked the right article first for 3 of 6, against 5 of 6 for embeddings alone.
Fusion is only as good as its inputs: measure it on your queries.
Practise the rest
6 Hybrid & reranking questions, 492 in all, each with a model answer. Free.
More Hybrid & reranking interview questions
- What is hybrid search?
- How does reciprocal rank fusion work, and why use ranks rather than scores?
- What's the difference between an embedding model and a reranker?
- How do you size the candidate pool for a reranker?
- A reranker fixes most of your misses but still prefers “safe for children over three” to “not safe for children under three”. What do you conclude?