DBLGNov 6, 2024

Towards Optimizing SQL Generation via LLM Routing

arXiv:2411.04319v18 citationsh-index: 48
Originality Incremental advance
AI Analysis

This addresses cost and efficiency issues for users of Text-to-SQL systems, though it is incremental as it builds on existing LLM capabilities.

The paper tackles the problem of unnecessary latency and cost in Text-to-SQL systems by introducing an LLM routing approach that dynamically selects cost-effective models for each query, achieving comparable accuracy to the most capable LLM while reducing costs.

Text-to-SQL enables users to interact with databases through natural language, simplifying access to structured data. Although highly capable large language models (LLMs) achieve strong accuracy for complex queries, they incur unnecessary latency and dollar cost for simpler ones. In this paper, we introduce the first LLM routing approach for Text-to-SQL, which dynamically selects the most cost-effective LLM capable of generating accurate SQL for each query. We present two routing strategies (score- and classification-based) that achieve accuracy comparable to the most capable LLM while reducing costs. We design the routers for ease of training and efficient inference. In our experiments, we highlight a practical and explainable accuracy-cost trade-off on the BIRD dataset.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes