mlsanityData to 14 Oct 2026

Towards Scalable Schema Mapping using Large Language Models

arXiv 2505.24716 ↗First posted 30 May 2025cs.DB cs.AIcited by 3

Not on the map. Why?

Abstract (arXiv)

The growing need to integrate information from a large number of diverse sources poses significant scalability challenges for data integration systems. These systems often rely on manually written schema mappings, which are complex, source-specific, and costly to maintain as sources evolve. While recent advances suggest that large language models (LLMs) can assist in automating schema matching by leveraging both structural and natural language cues, key challenges remain. In this paper, we identify three core issues with using LLMs for schema mapping: (1) inconsistent outputs due to sensitivity to input phrasing and structure, which we propose methods to address through sampling and aggregation techniques; (2) the need for more expressive mappings (e.g., GLaV), which strain the limited context windows of LLMs; and (3) the computational cost of repeated LLM calls, which we propose to mitigate through strategies like data type prefiltering.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 15 of its 40 references that are in the map. First posted on arXiv 30 May 2025.

Builds on

15 of 40 references.

References · 15

  1. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  2. 2022Large Language Models are Zero-Shot Reasonerscited by 4,374
  3. 2023Large Language Models Can Be Easily Distracted by Irrelevant Contextcited by 841
  4. 2023A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPTcited by 619
  5. 2022Can Foundation Models Wrangle Your Data?cited by 175
  6. 2022Natural Language to Code Translation with Executioncited by 124
  7. 2023Table Meets LLM: Can Large Language Models Understand Structured Table Data? A Benchmark and Empirical Studycited by 116
  8. 2023Language Models Enable Simple Systems for Generating Structured Views of Heterogeneous Data Lakescited by 111
  9. 2023Tabular Representation, Noisy Operators, and Impacts on Table Structure Understanding Tasks in LLMscited by 49
  10. 2023Large Language Models as Data Preprocessorscited by 34
  11. 2024Schema Matching with Large Language Models: an Experimental Studycited by 20
  12. 2024ReMatch: Retrieval Enhanced Schema Matching with LLMscited by 16
3 more
  1. 2024LLM-RankFusion: Mitigating Intrinsic Inconsistency in LLM-based Rankingcited by 16
  2. 2024KcMF: A Knowledge-compliant Framework for Schema and Entity Matching with Fine-tuning-free LLMscited by 8
  3. 2024GRAM: Generative Retrieval Augmented Matching of Data Schemas in the Context of Data Securitycited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Can LLMs Clean Up Your Mess? A Survey of Application-Ready Data Preparation with LLMscited by 9
  2. 2026Orthogonal Hierarchical Decomposition for Structure-Aware Table Understanding with Large Language Modelscited by 1
  3. 2026Towards automated data analysis: A guided framework for LLM-based risk estimationcited by 0