Large Language Models for Information Retrieval: A Survey
Introduction retrieval upstream - query reformulation downstream - reranking and reading reranking only on a limited set of relevant documents personalization, diversification Background Info retrieval relevance estimation - lexical similarity between the query and document vectors. Components Query rewriter Retriever Reranker - fine-grained reordering Reader - comprehend real-time user intent and generate dynamic responses Search agent LLMs Query rewriter Rewriting scenario