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

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.

19 pages, 9 figures, Accepted by UIST 2025

References in corpus (9)

• The Power of Noise: Redefining Retrieval for RAG Systems
• Retrieval-Enhanced Machine Learning
• WaitGPT: Monitoring and Steering Conversational LLM Agent in Data Analysis with On-the-Fly Code Visualization
• KNOWNET: Guided Health Information Seeking from LLMs via Knowledge Graph Integration
• KnowledgeVIS: Interpreting Language Models by Comparing Fill-in-the-Blank Prompts
• Angler: Helping Machine Translation Practitioners Prioritize Model Improvements
• CommonsenseVIS: Visualizing and Understanding Commonsense Reasoning Capabilities of Natural Language Models
• iScore: Visual Analytics for Interpreting How Language Models Automatically Score Summaries
• DeepLens: Interactive Out-of-distribution Data Detection in NLP Models