BM25 is a ranking function used in information retrieval to estimate the relevance of documents to a given search query. It's a sparse retrieval method that calculates a score for each document based on term frequency, inverse document frequency, and document length normalization.
BM25 is a fundamental search algorithm that helps find the most relevant documents for a given query. It's often used in AI systems, especially those that combine large language models with external knowledge, to ensure the AI has accurate information and avoids making things up.
Okapi BM25, BM25F, BM25+
Was this definition helpful?