ListK: Semantic ORDER BY and LIMIT K with Listwise Prompting

2026-03-17

AI Summary

Existing semantic ranking and Top-K query methods struggle to balance latency and accuracy when handling semi-structured, unstructured, and multimodal data. This work proposes ListK, a novel framework that introduces, for the first time, list-based multi-pivot quickselect and quicksort algorithms (LMPQSelect/LMPQSort) and designs deterministic list tournaments (LTTopK), Las Vegas strategies, and Monte Carlo list tournament filters (LTFilter). Through a recall-driven query optimization mechanism, ListK dynamically selects the optimal physical operator, reducing latency by nearly 50% with negligible loss in recall and NDCG. The approach substantially outperforms state-of-the-art methods and consistently dominates the performance Pareto frontier.

Technology Category

• Search and Optimization: Distributed Search
• Data Mining & Knowledge Management: Intelligent Query Processing
• Machine Learning: Learning Preferences or Rankings

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Querying, indexing, and retrieval in Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Semantic operators abstract large language model (LLM) calls in SQL clauses. It is gaining traction as an easy method to analyze semi-structured, unstructured, and multimodal datasets. While a plethora of recent works optimize various semantic operators, existing methods for semantic ORDER BY (full sort) and LIMIT K (top-K) remain lackluster. Our ListK framework improves the latency of semantic ORDER BY ... LIMIT K at no cost to accuracy. Motivated by the recent advance in fine-tuned listwise rankers, we study several sorting algorithms that best combine partial listwise rankings. These include: 1) deterministic listwise tournament (LTTopK), 2) Las Vegas and embarrassingly parallel listwise multi-pivot quickselect/sort (LMPQSelect, LMPQSort), and 3) a basic Monte Carlo listwise tournament filter (LTFilter). Of these, listwise multi-pivot quickselect/sort are studied here for the first time. The full framework provides a query optimizer for combining the above physical operators based on the target recall to minimize latency. We provide theoretical analysis to easily tune parameters and provide cost estimates for query optimizers. ListK empirically dominates the Pareto frontier, halving latency at virtually no cost to recall and NDCG compared to prior art.

Problem

• semantic ORDER BY
• LIMIT K
• listwise prompting
• top-K retrieval
• LLM-based sorting

Innovation

• Listwise Prompting
• Semantic SQL
• Top-K Retrieval
• Multi-Pivot Quickselect
• Query Optimization