mlsanityData to 14 Oct 2026

Research Challenges in Relational Database Management Systems for LLM Queries

arXiv 2508.20912 ↗First posted 28 Aug 2025cs.DB cs.AIcited by 2

Not on the map. Why?

Abstract (arXiv)

Large language models (LLMs) have become essential for applications such as text summarization, sentiment analysis, and automated question-answering. Recently, LLMs have also been integrated into relational database management systems to enhance querying and support advanced data processing. Companies such as Amazon, Databricks, Google, and Snowflake offer LLM invocation directly within SQL, denoted as LLM queries, to boost data insights. However, open-source solutions currently have limited functionality and poor performance. In this work, we present an early exploration of two open-source systems and one enterprise platform, using five representative queries to expose functional, performance, and scalability limits in today's SQL-invoked LLM integrations. We identify three main issues: enforcing structured outputs, optimizing resource utilization, and improving query planning. We implemented initial solutions and observed improvements in accommodating LLM powered SQL queries. These early gains demonstrate that tighter integration of LLM+DBMS is the key to scalable and efficient processing of LLM queries.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 15 of its 46 references that are in the map. First posted on arXiv 28 Aug 2025.

Builds on

15 of 46 references.

References · 15

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  3. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  4. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,418
  5. 2018Know What You Don't Know: Unanswerable Questions for SQuADcited by 1,554
  6. 2024Large Language Models(LLMs) on Tabular Data: Prediction, Generation, and Understanding -- A Surveycited by 159
  7. 2024Jasper and Stella: distillation of SOTA embedding modelscited by 112
  8. 2024Optimized Feature Generation for Tabular Data via LLMs with Decision Tree Reasoningcited by 49
  9. 2024A Declarative System for Optimizing AI Workloadscited by 37
  10. 2025A Closer Look at System Prompt Robustnesscited by 32
  11. 2024UQE: A Query Engine for Unstructured Databasescited by 21
  12. 2025TARGET: Benchmarking Table Retrieval for Generative Taskscited by 17
3 more
  1. 2024HARMONIC: Harnessing LLMs for Tabular Data Synthesis and Privacy Protectioncited by 16
  2. 2025Beyond Quacking: Deep Integration of Language Models and RAG into DuckDBcited by 15
  3. 2025Tabby: A Language Model Architecture for Tabular and Structured Data Synthesiscited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Beyond Linear LLM Invocation: An Efficient and Effective Semantic Filter Paradigmcited by 1
  2. 2026LLM+Graph@VLDB'2025 Workshop Summarycited by 0