# Query Performance Explanation through Large Language Model for HTAP Systems

arXiv: https://arxiv.org/abs/2412.01709 · HTML: https://mlsanity.com/paper/2412.01709/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 23 references that are in the map.
- First posted on arXiv 2 Dec 2024.

## Builds on (most cited first, 12 of 12)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs](https://mlsanity.com/paper/1603.09320/) (2016)
- [Bao: Learning to Steer Query Optimizers](https://mlsanity.com/paper/2004.03814/) (2020)
- [D-Bot: Database Diagnosis System using Large Language Models](https://mlsanity.com/paper/2312.01454/) (2023)
- [Lero: A Learning-to-Rank Query Optimizer](https://mlsanity.com/paper/2302.06873/) (2023)
- [Evaluating the Data Model Robustness of Text-to-SQL Systems Based on Real User Queries](https://mlsanity.com/paper/2402.08349/) (2024)
- [COOOL: A Learning-To-Rank Approach for SQL Hint Recommendations](https://mlsanity.com/paper/2304.04407/) (2023)
- [Evaluating SQL Understanding in Large Language Models](https://mlsanity.com/paper/2410.10680/) (2024)

## Built on by (most cited first, 1 of 1)

- [Data Agents: Agentic Data Systems](https://mlsanity.com/paper/2609.24137/) (2026)

## Abstract (arXiv)

In hybrid transactional and analytical processing (HTAP) systems, users often struggle to understand why query plans from one engine (OLAP or OLTP) perform significantly slower than those from another. Although optimizers provide plan details via the EXPLAIN function, these explanations are frequently too technical for non-experts and offer limited insights into performance differences across engines. To address this, we propose a novel framework that leverages large language models (LLMs) to explain query performance in HTAP systems. Built on Retrieval-Augmented Generation (RAG), our framework constructs a knowledge base that stores historical query executions and expert-curated explanations. To enable efficient retrieval of relevant knowledge, query plans are embedded using a lightweight tree-CNN classifier. This augmentation allows the LLM to generate clear, context-aware explanations of performance differences between engines. Our approach demonstrates the potential of LLMs in hybrid engine systems, paving the way for further advancements in database optimization and user support.