A Survey of Query Refinement Techniques From Neural Architectures to Practical Applications
Bibliographic record
Abstract
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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.007 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.003 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.004 | 0.002 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".