A Survey of LLM $\times$ DATA

TL;DR

This survey explores the evolving relationship between large language models and data management, highlighting how data feeds LLMs and how LLMs are transforming data handling and analysis.

Contribution

It provides a comprehensive review of recent advances in the bidirectional integration of LLMs and data management, covering data processing, storage, serving, and LLM-driven data manipulation and analysis.

Findings

Data processing techniques for LLMs include scalable acquisition and synthetic augmentation.

Efficient data storage and retrieval strategies are crucial for LLM performance.

LLMs are increasingly used for data cleaning, integration, and system optimization.

Abstract

The integration of large language model (LLM) and data management (DATA) is rapidly redefining both domains. In this survey, we comprehensively review the bidirectional relationships. On the one hand, DATA4LLM, spanning large-scale data processing, storage, and serving, feeds LLMs with high quality, diversity, and timeliness of data required for stages like pre-training, post-training, retrieval-augmented generation, and agentic workflows: (i) Data processing for LLMs includes scalable acquisition, deduplication, filtering, selection, domain mixing, and synthetic augmentation; (ii) Data Storage for LLMs focuses on efficient data and model formats, distributed and heterogeneous storage hierarchies, KV-cache management, and fault-tolerant checkpointing; (iii) Data serving for LLMs tackles challenges in RAG (e.g., knowledge post-processing), LLM inference (e.g., prompt compression, data provenance), and training strategies (e.g., data packing and shuffling). On the other hand, in LLM4DATA, LLMs are emerging as general-purpose engines for data management. We review recent advances in (i) data manipulation, including automatic data cleaning, integration, discovery; (ii) data analysis, covering reasoning over structured, semi-structured, and unstructured data, and (iii) system optimization (e.g., configuration tuning, query rewriting, anomaly diagnosis), powered by LLM techniques like retrieval-augmented prompting, task-specialized fine-tuning, and multi-agent collaboration.