RAGTrace: Understanding and Refining Retrieval-Generation Dynamics in Retrieval-Augmented Generation

TL;DR

RAGTrace is an interactive system that analyzes and improves the retrieval and generation processes in Retrieval-Augmented Generation models, making their internal dynamics more transparent and controllable.

Contribution

The paper introduces RAGTrace, a novel evaluation system that provides multi-level analysis of retrieval-generation interactions in RAG workflows, addressing opacity issues.

Findings

Enables detailed analysis of retrieval and generation dynamics.

Supports domain-specific customization of retrieval processes.

Demonstrates effectiveness through real-world case studies.

Abstract

Retrieval-Augmented Generation (RAG) systems have emerged as a promising solution to enhance large language models (LLMs) by integrating external knowledge retrieval with generative capabilities. While significant advancements have been made in improving retrieval accuracy and response quality, a critical challenge remains that the internal knowledge integration and retrieval-generation interactions in RAG workflows are largely opaque. This paper introduces RAGTrace, an interactive evaluation system designed to analyze retrieval and generation dynamics in RAG-based workflows. Informed by a comprehensive literature review and expert interviews, the system supports a multi-level analysis approach, ranging from high-level performance evaluation to fine-grained examination of retrieval relevance, generation fidelity, and cross-component interactions. Unlike conventional evaluation practices that focus on isolated retrieval or generation quality assessments, RAGTrace enables an integrated exploration of retrieval-generation relationships, allowing users to trace knowledge sources and identify potential failure cases. The system's workflow allows users to build, evaluate, and iterate on retrieval processes tailored to their specific domains of interest. The effectiveness of the system is demonstrated through case studies and expert evaluations on real-world RAG applications.