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

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Da, Longchao, Shah, Parth Mitesh, Liou, Kuan-Ru, Zhang, Jiaxing, Wei, Hua
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912376748507136
author Da, Longchao
Shah, Parth Mitesh
Liou, Kuan-Ru
Zhang, Jiaxing
Wei, Hua
author_facet Da, Longchao
Shah, Parth Mitesh
Liou, Kuan-Ru
Zhang, Jiaxing
Wei, Hua
contents Large Language Models are now key assistants in human decision-making processes. However, a common note always seems to follow: "LLMs can make mistakes. Be careful with important info." This points to the reality that not all outputs from LLMs are dependable, and users must evaluate them manually. The challenge deepens as hallucinated responses, often presented with seemingly plausible explanations, create complications and raise trust issues among users. To tackle such issue, this paper proposes GE-Chat, a knowledge Graph enhanced retrieval-augmented generation framework to provide Evidence-based response generation. Specifically, when the user uploads a material document, a knowledge graph will be created, which helps construct a retrieval-augmented agent, enhancing the agent's responses with additional knowledge beyond its training corpus. Then we leverage Chain-of-Thought (CoT) logic generation, n-hop sub-graph searching, and entailment-based sentence generation to realize accurate evidence retrieval. We demonstrate that our method improves the existing models' performance in terms of identifying the exact evidence in a free-form context, providing a reliable way to examine the resources of LLM's conclusion and help with the judgment of the trustworthiness.
format Preprint
id arxiv_https___arxiv_org_abs_2505_10143
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle 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
Computation and Language
68T50, 68T30
I.2.7; I.2.4; H.3.3
Large Language Models are now key assistants in human decision-making processes. However, a common note always seems to follow: "LLMs can make mistakes. Be careful with important info." This points to the reality that not all outputs from LLMs are dependable, and users must evaluate them manually. The challenge deepens as hallucinated responses, often presented with seemingly plausible explanations, create complications and raise trust issues among users. To tackle such issue, this paper proposes GE-Chat, a knowledge Graph enhanced retrieval-augmented generation framework to provide Evidence-based response generation. Specifically, when the user uploads a material document, a knowledge graph will be created, which helps construct a retrieval-augmented agent, enhancing the agent's responses with additional knowledge beyond its training corpus. Then we leverage Chain-of-Thought (CoT) logic generation, n-hop sub-graph searching, and entailment-based sentence generation to realize accurate evidence retrieval. We demonstrate that our method improves the existing models' performance in terms of identifying the exact evidence in a free-form context, providing a reliable way to examine the resources of LLM's conclusion and help with the judgment of the trustworthiness.
title GE-Chat: A Graph Enhanced RAG Framework for Evidential Response Generation of LLMs
topic Computation and Language
68T50, 68T30
I.2.7; I.2.4; H.3.3
url https://arxiv.org/abs/2505.10143