Recall and Precision
Metrics measuring how completely and accurately a system retrieves relevant results.
Definition
Recall and precision are fundamental metrics for evaluating retrieval and extraction systems. Recall measures completeness: what percentage of relevant items were found. Precision measures accuracy: what percentage of returned items were actually relevant. There is typically a trade-off between these metrics. High-stakes applications may prioritise recall to avoid missing important information, while user-facing search may prioritise precision to avoid overwhelming users with irrelevant results.
More in Core Concepts
Grounding
Connecting AI responses to verified source documents to ensure accuracy.
Hybrid Search
Combining keyword and semantic search for more comprehensive results.
Retrieval Augmented Generation (RAG)
A technique that grounds AI responses in retrieved documents for accurate, cited answers.
Semantic Search
Search that understands the meaning of queries rather than just matching keywords.
See Recall in action
Understanding the terminology is the first step. See how Conductor applies these concepts to solve real document intelligence challenges.
Request a demo