mlsanityData to 14 Oct 2026

Tackling prediction tasks in relational databases with LLMs

arXiv 2411.11829 ↗First posted 18 Nov 2024cs.LG cs.CL cs.DBcited by 14

Not on the map. Why?

Abstract (arXiv)

Though large language models (LLMs) have demonstrated exceptional performance across numerous problems, their application to predictive tasks in relational databases remains largely unexplored. In this work, we address the notion that LLMs cannot yield satisfactory results on relational databases due to their interconnected tables, complex relationships, and heterogeneous data types. Using the recently introduced RelBench benchmark, we demonstrate that even a straightforward application of LLMs achieves competitive performance on these tasks. These findings establish LLMs as a promising new baseline for ML on relational databases and encourage further research in this direction.

Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). Builds on 15 of its 28 references that are in the map. First posted on arXiv 18 Nov 2024.

Builds on

15 of 28 references.

References · 15

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2024The Llama 3 Herd of Modelscited by 14,715
  3. 2017Inductive Representation Learning on Large Graphscited by 6,320
  4. 2017Neural Message Passing for Quantum Chemistrycited by 3,487
  5. 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,139
  6. 2021Revisiting Deep Learning Models for Tabular Datacited by 740
  7. 2023Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLscited by 688
  8. 2021Identity-aware Graph Neural Networkscited by 198
  9. 2024RelBench: A Benchmark for Deep Learning on Relational Databasescited by 96
  10. 2024Large Scale Transfer Learning for Tabular Data via Language Modelingcited by 76
  11. 2023Relational Deep Learning: Graph Representation Learning on Relational Databasescited by 56
  12. 2023Tabular Representation, Noisy Operators, and Impacts on Table Structure Understanding Tasks in LLMscited by 49
3 more
  1. 2021GitTables: A Large-Scale Corpus of Relational Tablescited by 45
  2. 2024rLLM: Relational Table Learning with LLMscited by 7
  3. 2024TabularFM: An Open Framework For Tabular Foundational Modelscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 5; 2026: 9.

14 papers.

Sort:

By area:

  1. 2025RelGNN: Composite Message Passing for Relational Deep Learningcited by 48
  2. 2025Relational Graph Transformercited by 34
  3. 2025Large Language Models are Good Relational Learnerscited by 24
  4. 2025Relational Deep Learning: Challenges, Foundations and Next-Generation Architecturescited by 23
  5. 2026KumoRFM-2: Scaling Foundation Models for Relational Learningcited by 19
  6. 2026No Need to Train Your RDB Foundation Modelcited by 10
  7. 2026RDBLearn: Simple In-Context Prediction Over Relational Databasescited by 5
  8. 2026OpenRFM: Dissecting Relational In-Context Learningcited by 4
  9. 2026ReFuGe: Feature Generation for Prediction Tasks on Relational Databases with LLM Agentscited by 3
  10. 2025LATTLE: LLM Attention Transplant for Transfer Learning of Tabular Data Across Disparate Domainscited by 2
  11. 2026Relatron: Automating Relational Machine Learning over Relational Databasescited by 2
  12. 2026RelAgent: LLM Agents as Data Scientists for Relational Learningcited by 2
2 more
  1. 2026InvWeaver: Deductive Feedback for Invariant Synthesis in Interacting-Loop Programscited by 0
  2. 2026STEER: Reducing Inference Cost in Relational Foundation Models through Semantically Informed Samplingcited by 0