core practice · coding problem
Cross-encoder rerank top-k
Retrieve top-5 by BM25, then rerank with scores [0.9,0.2,0.8,0.1,0.7] for query "payment API". Return new order.
The mechanism
Retrieval is recall-oriented and cheap; reranking is precision-oriented and expensive. Retrieve ~100 candidates fast, then run a heavier cross-encoder on just those to reorder the top 10.
Expected evidence
Doc0, Doc2, Doc4, Doc1, Doc3.
Try this drill in the practice workspace →
Hints when you need them
- Reranker sees query+doc jointly.
- Only score the small candidate set.
Watch for these mistakes
- Reranking the whole corpus instead of a candidate set
- Adding a reranker without measuring latency budget
- Not checking that reranking actually beats the retriever on evals