ChatDB: Augmenting LLMs with Databases as Their Symbolic Memory

2023/06/06 by Chenxu Hu, Hu, Chenxu, Jie Fu +9 · 10 citations
Computer Science · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #Databases (cs.DB) #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Natural Language Processing Techniques #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2306.03901

openalex publication_date 2023/06/06 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Large language models (LLMs) with memory are computationally universal. However, mainstream LLMs are not taking full advantage of memory, and the designs are heavily influenced by biological brains. Due to their approximate nature and proneness to the accumulation of errors, conventional neural memory mechanisms cannot support LLMs to simulate complex reasoning. In this paper, we seek inspiration from modern computer architectures to augment LLMs with symbolic memory for complex multi-hop reasoning. Such a symbolic memory framework is instantiated as an LLM and a set of SQL databases, where the LLM generates SQL instructions to manipulate the SQL databases. We validate the effectiveness of the proposed memory framework on a synthetic dataset requiring complex reasoning. The project website is available at https://chatdatabase.github.io/ .

Cited by

• ConsistencyGate: Preventing Memory Contamination in LLM Agents via Self-Consistency Admission Control
• TableGPT-R1: Advancing Tabular Reasoning Through Reinforcement Learning
• SEAL: Self-Evolving Agentic Learning for Conversational Question Answering over Knowledge Graphs
• Know Your Intent: An Autonomous Multi-Perspective LLM Agent Framework for DeFi User Transaction Intent Mining
• Empowering Real-World: A Survey on the Technology, Practice, and Evaluation of LLM-driven Industry Agents
• MEMTRACK: Evaluating Long-Term Memory and State Tracking in Multi-Platform Dynamic Agent Environments
• Bridging Inference-Time Scaling and Episodic Memory with Action-Centric Graphs
• A Survey on Retrieval And Structuring Augmented Generation with Large Language Models
• A Multi-Memory Segment System for Generating High-Quality Long-Term Memory Content in Agents
• Guided Navigation in Knowledge-Dense Environments: Structured Semantic Exploration with Guidance Graphs

Related

• ChatLogic: Integrating Logic Programming with Large Language Models for Multi-Step Reasoning
• PTD-SQL: Partitioning and Targeted Drilling with LLMs in Text-to-SQL
• Trustworthy and Efficient LLMs Meet Databases
• From Isolated Conversations to Hierarchical Schemas: Dynamic Tree Memory Representation for LLMs
• MoT: Memory-of-Thought Enables ChatGPT to Self-Improve