paper-with-me

Papers

ChatDB: Augmenting LLMs with Databases as Their Symbolic Memory

2023-06-06 · Chenxu Hu, Jie Fu, Chenzhuang Du, Simian Luo, Junbo Zhao, Hang Zhao

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/ .

📄 PDF Abstract BibTeX arXiv:2306.03901

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

ChatDBG: Augmenting Debugging with Large Language Models

2024-03-25 · Kyla H. Levin, Nicolas van Kempen, Emery D. Berger, Stephen N. Freund

Debugging is a critical but challenging task for programmers. This paper proposes ChatDBG, an AI-powered debugging assistant. ChatDBG integrates large language models (LLMs) to significantly enhance the capabilities and …

C++ codeNavigateWorld Knowledge

Code-as-Symbolic-Planner: Foundation Model-Based Robot Planning via Symbolic Code Generation

2025-03-03 · Yongchao Chen, Yilun Hao, Yang Zhang, Chuchu Fan

Recent works have shown great potentials of Large Language Models (LLMs) in robot task and motion planning (TAMP). Current LLM approaches generate text- or code-based reasoning chains with sub-goals and action plans. How…

Code GenerationCommon Sense ReasoningMotion PlanningTask and Motion Planning

Symbolic Working Memory Enhances Language Models for Complex Rule Application

2024-08-24 · Siyuan Wang, Zhongyu Wei, Yejin Choi, Xiang Ren

Large Language Models (LLMs) have shown remarkable reasoning performance but struggle with multi-step deductive reasoning involving a series of rule application steps, especially when rules are presented non-sequentially…

Human-Centered Planning

2023-11-08 · Yuliang Li, Nitin Kamra, Ruta Desai, Alon Halevy

LLMs have recently made impressive inroads on tasks whose output is structured, such as coding, robotic planning and querying databases. The vision of creating AI-powered personal assistants also involves creating struct…

Prompt-Time Symbolic Knowledge Capture with Large Language Models

2024-02-01 · Tolga Çöplü, Arto Bendiken, Andrii Skomorokhov, Eduard Bateiko 외

Augmenting large language models (LLMs) with user-specific knowledge is crucial for real-world applications, such as personal AI assistants. However, LLMs inherently lack mechanisms for prompt-driven knowledge capture. T…

Knowledge Graphs