LeReRAG: Measuring Legal Relevance in Retrieval Augmented Generation Applications
Abstract
Retrieval Augmented Generation (RAG) is starting to be used in professional settings like the legal domain. In classic information retrieval (IR) systems, the effectiveness of the system is often evaluated using measures that rely on relevance judgements. Van Opijnen and Santos [1] have created a framework of relevance for information retrieval systems for legal professionals, to ground these evaluation methods. This paper takes their framework of relevance, and extends it for use with RAG applications. The aim of this framework is to make visible how legal RAG differs from other RAG applications, and how that might impact evaluation.
Read the paper
Related studies
- Knowledge Management Perspective of Generative Artificial Intelligence
- Navigating Generative Artificial Intelligence Promises and Perils for Knowledge and Creative Work
- Characterizing the evolving research on enterprise content management
- Large language models and multimodal foundation models for precision oncology
- From Generative AI to Extended Reality: Multidisciplinary Perspectives on the Challenges, Opportunities, and Future of Educational Computing
- Generative Artificial Intelligence: A New Engine for Advancing Environmental Science and Engineering
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.