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

TL;DR

GE-Chat is a framework that enhances large language models with knowledge graphs and evidence retrieval to improve response accuracy and trustworthiness in decision-making support.

Contribution

The paper introduces a novel knowledge graph enhanced retrieval-augmented framework for evidential response generation in LLMs, improving trustworthiness and accuracy.

Findings

Improves evidence retrieval accuracy in LLM responses.

Enhances trustworthiness of LLM outputs with evidence-based explanations.

Utilizes chain-of-thought and entailment methods for precise evidence extraction.

Abstract

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.