A Survey of Query Refinement Techniques From Neural Architectures to Practical Applications

Query refinement plays a central role in modern information retrieval (IR) systems by improving query clarity, resolving ambiguity, and enhancing result relevance.This survey provides a comprehensive overview of the model architectures and application domains associated with query refinement techniques.The paper first examines classical non-neural models and then explores a range of neural architectures, including embedding-based methods, recurrent neural networks (RNNs), sequence-to-sequence (seq2seq) frameworks, and transformer-based models.Special attention is given to the progression from static representations to contextaware and generative approaches, with an emphasis on how these models capture user intent and session context.The study then reviews the deployment of query refinement methods across practical domains such as product search, music retrieval, job search, and personalized information access.These applications demonstrate the real-world impact of query refinement in handling ambiguous queries, adapting to user preferences, and improving overall retrieval performance.By highlighting key advancements and challenges, this survey offers insight into the current state and future direction of query refinement research.