A Socratic RAG Approach to Connect Natural Language Queries on Research Topics with Knowledge Organization Systems

2025-02-20

AI Summary

This study addresses the imprecise mapping between natural-language research queries and fine-grained semantic entities in Knowledge Organization Systems (KOS), aiming to bridge the semantic gap between users’ intuitive understanding and large-scale bibliometric repositories. To this end, we propose a novel Socratic-dialogue-driven Retrieval-Augmented Generation (RAG) framework that iteratively refines query semantics through multi-turn clarification and augments generation with targeted KOS entity retrieval, enabling high-precision, interpretable natural-language-to-KOS entity mapping. Leveraging this framework, we construct CollabNext—a human-centered knowledge graph specifically designed for Historically Black Colleges and Universities (HBCUs) and emerging scholars—to enhance visibility and traceable collaboration for historically marginalized academic communities. Experimental results demonstrate significant improvements in cross-disciplinary topic discovery accuracy and scholarly relationship inference, establishing a new paradigm for equitable, transparent, and explainable intelligent scholarly services.

Technology Category

• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Knowledge Representation and Reasoning: Knowledge Acquisition
• Application Domains: Humanities & Computational Social Science

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Querying, indexing, and retrieval in Web-related graphs

Abstract

In this paper, we propose a Retrieval Augmented Generation (RAG) agent that maps natural language queries about research topics to precise, machine-interpretable semantic entities. Our approach combines RAG with Socratic dialogue to align a user's intuitive understanding of research topics with established Knowledge Organization Systems (KOSs). The proposed approach will effectively bridge"little semantics"(domain-specific KOS structures) with"big semantics"(broad bibliometric repositories), making complex academic taxonomies more accessible. Such agents have the potential for broad use. We illustrate with a sample application called CollabNext, which is a person-centric knowledge graph connecting people, organizations, and research topics. We further describe how the application design has an intentional focus on HBCUs and emerging researchers to raise visibility of people historically rendered invisible in the current science system.

Problem

• Map natural language queries to semantic entities
• Align user understanding with Knowledge Organization Systems
• Bridge domain-specific KOS with broad repositories

Innovation

• RAG agent maps queries
• Socratic dialogue aligns understanding
• Bridges domain KOS with repositories