Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

AGENTiGraph: An Interactive Knowledge Graph Platform for LLM-based Chatbots Utilizing Private Data

Xinjie Zhao, Moritz Blum, Rui Yang, Boming Yang, Luis Márquez Carpintero, Mónica Pina-Navarro, Tony Wang, Xin Li, Huitao Li, Yanran Fu, Rongrong Wang, Juntao Zhang, Irene Li

TL;DR

AGENTiGraph (Adaptive Generative ENgine for Task-based Interaction and Graphical Representation), a platform for knowledge management through natural language interaction that employs a multi-agent architecture to dynamically interpret user intents, manage tasks, and integrate new knowledge, ensures adaptability to evolving user requirements and data contexts.

Abstract

Large Language Models~(LLMs) have demonstrated capabilities across various applications but face challenges such as hallucination, limited reasoning abilities, and factual inconsistencies, especially when tackling complex, domain-specific tasks like question answering~(QA). While Knowledge Graphs~(KGs) have been shown to help mitigate these issues, research on the integration of LLMs with background KGs remains limited. In particular, user accessibility and the flexibility of the underlying KG have not been thoroughly explored. We introduce AGENTiGraph (Adaptive Generative ENgine for Task-based Interaction and Graphical Representation), a platform for knowledge management through natural language interaction. It integrates knowledge extraction, integration, and real-time visualization. AGENTiGraph employs a multi-agent architecture to dynamically interpret user intents, manage tasks, and integrate new knowledge, ensuring adaptability to evolving user requirements and data contexts. Our approach demonstrates superior performance in knowledge graph interactions, particularly for complex domain-specific tasks. Experimental results on a dataset of 3,500 test cases show AGENTiGraph significantly outperforms state-of-the-art zero-shot baselines, achieving 95.12\% accuracy in task classification and 90.45\% success rate in task execution. User studies corroborate its effectiveness in real-world scenarios. To showcase versatility, we extended AGENTiGraph to legislation and healthcare domains, constructing specialized KGs capable of answering complex queries in legal and medical contexts.

AGENTiGraph: An Interactive Knowledge Graph Platform for LLM-based Chatbots Utilizing Private Data

TL;DR

AGENTiGraph (Adaptive Generative ENgine for Task-based Interaction and Graphical Representation), a platform for knowledge management through natural language interaction that employs a multi-agent architecture to dynamically interpret user intents, manage tasks, and integrate new knowledge, ensures adaptability to evolving user requirements and data contexts.

Abstract

Large Language Models~(LLMs) have demonstrated capabilities across various applications but face challenges such as hallucination, limited reasoning abilities, and factual inconsistencies, especially when tackling complex, domain-specific tasks like question answering~(QA). While Knowledge Graphs~(KGs) have been shown to help mitigate these issues, research on the integration of LLMs with background KGs remains limited. In particular, user accessibility and the flexibility of the underlying KG have not been thoroughly explored. We introduce AGENTiGraph (Adaptive Generative ENgine for Task-based Interaction and Graphical Representation), a platform for knowledge management through natural language interaction. It integrates knowledge extraction, integration, and real-time visualization. AGENTiGraph employs a multi-agent architecture to dynamically interpret user intents, manage tasks, and integrate new knowledge, ensuring adaptability to evolving user requirements and data contexts. Our approach demonstrates superior performance in knowledge graph interactions, particularly for complex domain-specific tasks. Experimental results on a dataset of 3,500 test cases show AGENTiGraph significantly outperforms state-of-the-art zero-shot baselines, achieving 95.12\% accuracy in task classification and 90.45\% success rate in task execution. User studies corroborate its effectiveness in real-world scenarios. To showcase versatility, we extended AGENTiGraph to legislation and healthcare domains, constructing specialized KGs capable of answering complex queries in legal and medical contexts.

Paper Structure

This paper contains 56 sections, 7 figures, 4 tables.

Table of Contents

  1. Introduction
  2. AGENTiGraph Framework Design
  3. User Intent Interpretation.
  4. Key Concept Extraction
  5. Task Planning.
  6. Knowledge Graph Interaction.
  7. Reasoning.
  8. Response Generation.
  9. Dynamic Knowledge Integration.
  10. System Demonstration
  11. User Interface
  12. Task Design
  13. Evaluation
  14. Dataset and Experimental Setup
  15. User Intent Identification and Task Execution
  16. ...and 41 more sections

Figures (7)

  • Figure 1: AGENTiGraph Framework: A multi-agent system for intelligent KG interaction and management.
  • Figure 2: AGENTiGraph's Dual-Mode Interface: Conversational AI with Interactive Knowledge Exploration
  • Figure 3: Descriptions of pre-defined relations used to build the KGs.
  • Figure 4: This graph outlines the relationships between regulations and acts concerning biodiesel and excise duties.
  • Figure 5: This graph shows treatments for blood-related tumors and hematologic malignancies, including chemotherapy, hematopoietic stem cell transplantation, and CAR-T cell therapy (machine translated from Japanese to English).
  • ...and 2 more figures