TIGP (SNHCC) -- Making LLMs Find What You Really Need via Query Expansion
- 講者陳志明 博士 (中央研究院資訊科技創新研究中心)
邀請人:TIGP (SNHCC) - 時間2025-05-05 (Mon.) 14:00 ~ 16:00
- 地點資訊所新館106演講廳
摘要
Query expansion is a powerful technique that transforms basic user queries into richer, more comprehensive search terms for Retrieval-Augmented Generation (RAG) systems. When users ask questions in natural language, they often use different terminology than what appears in the knowledge base documents. By automatically expanding queries with synonyms, related concepts, and contextual terms, RAG systems can bridge this vocabulary gap and retrieve truly relevant information that might otherwise be missed. This presentation demonstrates how implementing query expansion can significantly enhance the accuracy and helpfulness of LLM-based systems, allowing them to better understand user intent and deliver more precise answers from your knowledge bases.