GRAM: Generative Retrieval Augmented Matching of Data Schemas in the Context of Data Security
On the map: Retrieval-augmented generation → Privacy and security of RAG
Abstract (arXiv)
Schema matching constitutes a pivotal phase in the data ingestion process for contemporary database systems. Its objective is to discern pairwise similarities between two sets of attributes, each associated with a distinct data table. This challenge emerges at the initial stages of data analytics, such as when incorporating a third-party table into existing databases to inform business insights. Given its significance in the realm of database systems, schema matching has been under investigation since the 2000s. This study revisits this foundational problem within the context of large language models. Adhering to increasingly stringent data security policies, our focus lies on the zero-shot and few-shot scenarios: the model should analyze only a minimal amount of customer data to execute the matching task, contrasting with the conventional approach of scrutinizing the entire data table. We emphasize that the zero-shot or few-shot assumption is imperative to safeguard the identity and privacy of customer data, even at the potential cost of accuracy. The capability to accurately match attributes under such stringent requirements distinguishes our work from previous literature in this domain.
Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Placed in Privacy and security of RAG, one of 15 directions in Retrieval-augmented generation. Builds on 17 of its 48 references that are in the map. First posted on arXiv 4 Jun 2024.
Builds on
17 of 48 references.
References · 17
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2022Training language models to follow instructions with human feedbackcited by 15,712
- 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
- 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
- 2020Scaling Laws for Neural Language Modelscited by 6,411
- 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
- 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
- 2022FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awarenesscited by 3,611
- 2022GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformerscited by 1,838
- 2022Fast Inference from Transformers via Speculative Decodingcited by 1,615
- 2022Large Language Models Are Human-Level Prompt Engineerscited by 1,020
- 2023The Flan Collection: Designing Data and Methods for Effective Instruction Tuningcited by 734
5 more
- 2018A Survey on Deep Learning for Named Entity Recognitioncited by 281
- 2023Accelerating Transformer Inference for Translation via Parallel Decodingcited by 123
- 2021Scale Efficiently: Insights from Pre-training and Fine-tuning Transformerscited by 105
- 2019Schema Matching using Machine Learningcited by 4
- 2022It's AI Match: A Two-Step Approach for Schema Matching Using Embeddingscited by 4
Built on by
Citing papers per year: 2024: 1; 2025: 2; 2026: 1.
4 papers.
- 2025Towards Scalable Schema Mapping using Large Language Modelscited by 3
- 2026Cost-Efficient RAG for Entity Matching with LLMs: A Blocking-based Explorationcited by 3
- 2024An Overview and Discussion on Using Large Language Models for Implementation Generation of Solutions to Open-Ended Problemscited by 0
- 2025Conceptual Schema Inference for Tabular Datasets using Large Language Modelscited by 0
- 2026Cost-Efficient RAG for Entity Matching with LLMs: A Blocking-based Exploration5 Feb 2026
- 2025Conceptual Schema Inference for Tabular Datasets using Large Language Models4 Sep 2025
- 2025Towards Scalable Schema Mapping using Large Language Models30 May 2025
- 2024An Overview and Discussion on Using Large Language Models for Implementation Generation of Solutions to Open-Ended Problems31 Dec 2024
Similar, not cited
Close in wording, no citation either way
- 2024Matchmaker: Self-Improving Large Language Model Programs for Schema Matching
- 2025TARGET: Benchmarking Table Retrieval for Generative Tasks
- 2026RACT: Retrieval Augmented Column-Table Learning and Prediction for Multi-Table Schema Matching
- 2025Generative Retrieval and Alignment Model: A New Paradigm for E-commerce Retrieval
- 2026OpenSanctions Pairs: Large-Scale Entity Matching with LLMs
- 2024Generating Is Believing: Membership Inference Attacks against Retrieval-Augmented Generation
- 2025Graph-Conditional Flow Matching for Relational Data Generation
- 2024Improving Retrieval-augmented Text-to-SQL with AST-based Ranking and Schema Pruning