GE-Chat: A Graph Enhanced RAG Framework for Evidential Response Generation of LLMs

Da, Longchao; Shah, Parth Mitesh; Liou, Kuan-Ru; Zhang, Jiaxing; Wei, Hua

doi:10.24963/ijcai.2025/1256

GE-Chat: A Graph Enhanced RAG Framework for Evidential Response Generation of LLMs

Longchao Da, Parth Mitesh Shah, Kuan-Ru Liou, Jiaxing Zhang, Hua Wei

Download BibTeX Cite

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence. Demo Track. Pages 11030-11033.

https://doi.org/10.24963/ijcai.2025/1256

Keywords

AI Ethics, Trust, Fairness: ETF: Trustworthy AI
Natural Language Processing: NLP: Applications
Natural Language Processing: NLP: Information extraction
Natural Language Processing: NLP: Interpretability and analysis of models for NLP

Abstract

Large Language Models (LLMs) have become integral to human decision-making processes. However, their outputs are not always reliable, often requiring users to assess the accuracy of the information provided manually. This issue is exacerbated by hallucinated responses, which are frequently presented with convincing but incorrect explanations, leading to trust concerns among users. To address this challenge, we propose GE-Chat, a knowledge Graph-enhanced retrieval-augmented generation framework designed to deliver Evidence-based responses. Specifically, when users upload a document, GE-Chat constructs a knowledge graph to support a retrieval-augmented agent, enriching the agent's responses with external knowledge beyond its training data. We further incorporate Chain-of-Thought (CoT) reasoning, n-hop subgraph searching, and entailment-based sentence generation to ensure accurate evidence retrieval. Experimental results demonstrate that our approach improves the ability of existing models to identify precise evidence in free-form contexts, offering a reliable mechanism for verifying LLM-generated conclusions and enhancing trustworthiness.

Longchao Da, Parth Mitesh Shah, Kuan-Ru Liou, Jiaxing Zhang, and Hua Wei. 2025. GE-Chat: A Graph Enhanced RAG Framework for Evidential Response Generation of LLMs. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25. IJCAI, 11030–11033. https://doi.org/10.24963/ijcai.2025/1256

@inproceedings{ijcai2025p1256,
  title     = {GE-Chat: A Graph Enhanced RAG Framework for Evidential Response Generation of LLMs},
  author    = {Da, Longchao and Shah, Parth Mitesh and Liou, Kuan-Ru and Zhang, Jiaxing and Wei, Hua},
  booktitle = {Proceedings of the Thirty-Fourth International Joint Conference on
               Artificial Intelligence, {IJCAI-25}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {James Kwok},
  pages     = {11030--11033},
  year      = {2025},
  month     = {8},
  note      = {Demo Track},
  doi       = {10.24963/ijcai.2025/1256},
  url       = {https://doi.org/10.24963/ijcai.2025/1256},
}

TY  - CPAPER
TI  - GE-Chat: A Graph Enhanced RAG Framework for Evidential Response Generation of LLMs
AU  - Da, Longchao
AU  - Shah, Parth Mitesh
AU  - Liou, Kuan-Ru
AU  - Zhang, Jiaxing
AU  - Wei, Hua
T2  - Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2025
SP  - 11030
EP  - 11033
DO  - 10.24963/ijcai.2025/1256
UR  - https://doi.org/10.24963/ijcai.2025/1256
ER  -