Interview: users complain search returns irrelevant results — how do you fix?
hardAnswer
- (1) Analyze query logs: are they specific / broad / navigational / typos?
- (2) Baseline: BM25 lexical.
- Add: (3) Dense retrieval (sentence-transformers).
- (4) Hybrid: BM25 + dense + RRF fusion.
- (5) Cross-encoder reranker on top 100 → top 10.
- (6) Query rewriting (HyDE / expansion for underspecified queries).
- (7) Feedback logging (clicks) → LTR fine-tuning.
- (8) A/B measure: click-through, dwell time, session success.
- (9) Evaluate with human relevance judgments quarterly.
Check yourself — multiple choice
- Just BM25
- Query log analysis + BM25 + dense retrieval + hybrid + RRF + cross-encoder rerank + query rewriting (HyDE) + LTR from clicks + CTR/dwell A/B + human judgments
- Random
- Not fixable
Search relevance: hybrid retrieval + rerank + rewrite + LTR + human judgments.
#interview#applications#nlp
Practise Unsupervised Learning
214 interview questions in this topic.
Related questions
- Interview: choose a sentence embedding model for a startup RAG.
- Interview: 'you have 1M support tickets — how do you categorize them?'
- Interview: 'you're asked to segment 10M customers — how?'
- Interview: 'design an unsupervised fraud detection system'.
- BM25 — why is it still competitive with modern retrievers?
- Vector search / approximate nearest neighbors — main algorithms.