Marcel: A Lightweight and Open-Source Conversational Agent for University Student Support

2025-07-18

AI Summary

To address delayed personalized responses and excessive administrative overhead in university admissions counseling, this paper proposes a lightweight, open-source dialogue support system. Methodologically, it integrates retrieval-augmented generation (RAG) with a configurable FAQ-matching module, featuring a novel semantic-mapping-based FAQ retriever that significantly improves knowledge-base recall accuracy—outperforming conventional dense and hybrid retrieval approaches—and supports administrator-driven fine-tuning. The system adopts a streamlined architecture with minimal computational resource requirements, making it well-suited for resource-constrained academic environments. Technical evaluation and real-world deployment demonstrate that the system meets target performance across response latency, personalization quality, and deployment feasibility. It effectively alleviates operational burdens on admissions teams and establishes a reusable, lightweight paradigm for practical AI deployment in education.

Technology Category

• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Natural Language Processing: Conversational AI/Dialog Systems
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

We present Marcel, a lightweight and open-source conversational agent designed to support prospective students with admission-related inquiries. The system aims to provide fast and personalized responses, while reducing workload of university staff. We employ retrieval-augmented generation to ground answers in university resources and to provide users with verifiable, contextually relevant information. To improve retrieval quality, we introduce an FAQ retriever that maps user questions to knowledge-base entries, allowing administrators to steer retrieval, and improving over standard dense/hybrid retrieval strategies. The system is engineered for easy deployment in resource-constrained academic settings. We detail the system architecture, provide a technical evaluation of its components, and report insights from a real-world deployment.

Problem

• Develops a lightweight chatbot for university admission inquiries
• Reduces staff workload with fast, personalized responses
• Improves answer accuracy using retrieval-augmented generation

Innovation

• Retrieval-augmented generation for verifiable answers
• FAQ retriever improves knowledge-base matching
• Lightweight design for resource-constrained deployment