Dynamic Trade-off Prediction In Multi-stage Retrieval Systems

Abstract

Modern multi-stage retrieval systems are comprised of a candidate generation stage followed by one or more reranking stages. In such an architecture, the quality of the final ranked list may not be sensitive to the quality of initial candidate pool, especially in terms of early precision. This provides several opportunities to increase retrieval efficiency without significantly sacrificing effectiveness. In this paper, we explore a new approach to dynamically predicting two different parameters in the candidate generation stage which can directly affect the overall efficiency and effectiveness of the entire system. Previous work exploring this tradeoff has focused on global parameter settings that apply to all queries, even though optimal settings vary across queries. In contrast, we propose a technique which makes a parameter prediction that maximizes efficiency within a effectiveness envelope on a per query basis, using only static pre-retrieval features. The query-specific tradeoff

Stats

• citations38
• S2 citations—
• github stars0
• HF likes0
• heat score11.93
• arxiv keyculpepper2016dynamic

Related papers

• Efficient And Effective Tail Latency Minimization In Multi-stage Retrieval Systems (2017)11.76
• Predicting Efficiency/effectiveness Trade-offs For Dense Vs. Sparse Retrieval Strategy Selection (2021)11.29
• DAT: Dynamic Alpha Tuning For Hybrid Retrieval In Retrieval-augmented Generation (2025)0.00
• Optimizing Retrieval Components For A Shared Backbone Via Component-wise Multi-stage Training (2026)0.00
• Optimizing Compound Retrieval Systems (2025)0.00
• Deep Retrieval: Learning A Retrievable Structure For Large-scale Recommendations (2020)0.00
• A Novel User Representation Paradigm For Making Personalized Candidate Retrieval (2019)0.00
• RADAR: Recall Augmentation Through Deferred Asynchronous Retrieval (2025)2.26