A Comparative Study of Retrieval Methods in Azure AI Search
By: Qiang Mao , Han Qin , Robert Neary and more
Increasingly, attorneys are interested in moving beyond keyword and semantic search to improve the efficiency of how they find key information during a document review task. Large language models (LLMs) are now seen as tools that attorneys can use to ask natural language questions of their data during document review to receive accurate and concise answers. This study evaluates retrieval strategies within Microsoft Azure's Retrieval-Augmented Generation (RAG) framework to identify effective approaches for Early Case Assessment (ECA) in eDiscovery. During ECA, legal teams analyze data at the outset of a matter to gain a general understanding of the data and attempt to determine key facts and risks before beginning full-scale review. In this paper, we compare the performance of Azure AI Search's keyword, semantic, vector, hybrid, and hybrid-semantic retrieval methods. We then present the accuracy, relevance, and consistency of each method's AI-generated responses. Legal practitioners can use the results of this study to enhance how they select RAG configurations in the future.
Similar Papers
A Reasoning-Focused Legal Retrieval Benchmark
Computation and Language
Helps lawyers find important legal information faster.
Augmented Question-guided Retrieval (AQgR) of Indian Case Law with LLM, RAG, and Structured Summaries
Information Retrieval
Finds important court cases by understanding legal questions.
Aligning LLMs for the Classroom with Knowledge-Based Retrieval -- A Comparative RAG Study
Artificial Intelligence
Makes AI answers for school more truthful.