Reranking
A second-stage ranking process that takes initial search results and reorders them using a more sophisticated model. Reranking improves precision by applying deeper analysis to a smaller candidate set.
Why It Matters
Reranking dramatically improves RAG quality. A cheap, fast retrieval step gets candidates, then an expensive, accurate reranker finds the truly relevant ones.
Example
Initial retrieval returns 100 documents, then a cross-encoder reranker scores each one more carefully and reorders them, surfacing the 5 most relevant to the top.
Think of it like...
Like a hiring process with resume screening (initial retrieval) followed by interviews (reranking) — the first pass narrows the field, the second identifies the best candidates.
Related Terms
Retrieval
The process of finding and extracting relevant information from a large collection of documents or data in response to a query. In AI systems, retrieval is often the first step before generation.
Semantic Search
Search that understands the meaning and intent behind a query rather than just matching keywords. It uses embeddings to find results that are conceptually related even if they use different words.
Cross-Encoder
A model that takes two texts as input simultaneously and outputs a relevance or similarity score. Unlike bi-encoders, cross-encoders consider the full interaction between both texts.
Retrieval-Augmented Generation
A technique that enhances LLM outputs by first retrieving relevant information from external knowledge sources and then using that information as context for generation. RAG combines the power of search with the fluency of language models.