TrustRAG: An Information Assistant with Retrieval Augmented Generation

TL;DR

TrustRAG is a new framework that improves the trustworthiness of retrieval-augmented generation models by enhancing indexing, retrieval, and citation accuracy, with open-source tools and a demonstration studio.

Contribution

It introduces semantic-enhanced chunking, utility-based filtering, and fine-grained citation techniques to improve RAG system reliability and trustworthiness.

Findings

Enhanced semantic completeness in indexing

Improved retrieval quality with filtering

More accurate citation and opinion detection

Abstract

\Ac{RAG} has emerged as a crucial technique for enhancing large models with real-time and domain-specific knowledge. While numerous improvements and open-source tools have been proposed to refine the \ac{RAG} framework for accuracy, relatively little attention has been given to improving the trustworthiness of generated results. To address this gap, we introduce TrustRAG, a novel framework that enhances \ac{RAG} from three perspectives: indexing, retrieval, and generation. Specifically, in the indexing stage, we propose a semantic-enhanced chunking strategy that incorporates hierarchical indexing to supplement each chunk with contextual information, ensuring semantic completeness. In the retrieval stage, we introduce a utility-based filtering mechanism to identify high-quality information, supporting answer generation while reducing input length. In the generation stage, we propose fine-grained citation enhancement, which detects opinion-bearing sentences in responses and infers citation relationships at the sentence-level, thereby improving citation accuracy. We open-source the TrustRAG framework and provide a demonstration studio designed for excerpt-based question answering tasks \footnote{https://huggingface.co/spaces/golaxy/TrustRAG}. Based on these, we aim to help researchers: 1) systematically enhancing the trustworthiness of \ac{RAG} systems and (2) developing their own \ac{RAG} systems with more reliable outputs.