Anonymized Experimental Results for a Multimodal Agentic RAG Framework in Higher Education Information Services
Abstract
This dataset provides anonymized experimental results supporting the study entitled “A Study on a Multimodal Agentic RAG Framework for Integrating Multi-Source Heterogeneous Information in Higher Education Institutions”.The study investigates a multimodal Agentic Retrieval-Augmented Generation framework designed to integrate multi-source and heterogeneous university information and provide a natural-language question-answering portal for higher education scenarios. The framework combines visual-language-model-based multimodal semantic textification, hybrid retrieval using BM25 sparse retrieval and dense vector retrieval, real-time online retrieval, and an agent-based dynamic routing mechanism.The released files include anonymized questionnaire/survey-related data and experimental result tables used for framework validation and ablation analysis. The experimental dataset is based on a 630-item standardized test set constructed for university information retrieval and question-answering tasks. The released data include the classification of test samples by query complexity, question type, and input modality, as well as evaluation results for answer accuracy, factual consistency, evidence coverage, multimodal preprocessing ablation, hybrid retrieval ablation, and dynamic retrieval routing efficiency.For privacy and institutional information-protection reasons, the original campus messages, group-chat records, internal knowledge sources, raw query texts, screenshots, posters,…
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.