CHOIR: A Chatbot-mediated Organizational Memory Leveraging Communication in University Research Labs

2025-09-24

AI Summary

Knowledge in university research laboratories is highly fragmented across instant messaging (IM) records, impeding knowledge consolidation, retrieval, and sharing. Method: This paper introduces CHOIR—a privacy-aware chatbot powered by large language models (LLMs)—that integrates question-answering retrieval, dialogue-driven knowledge extraction, cross-user QA sharing, and AI-assisted dynamic documentation updating to establish a “IM–organizational memory” co-evolution paradigm. Contribution/Results: CHOIR pioneers an automated, end-to-end pipeline transforming unstructured IM dialogues into structured, actionable knowledge while enabling progressive refinement of personal insights into reusable organizational documents under strict privacy constraints. Deployed over one month across four laboratories, CHOIR processed 107 valid QA queries and triggered 38 intelligent document updates, demonstrating significant improvements in knowledge accessibility and continuity. The evaluation further uncovered a tension mechanism between privacy awareness and knowledge contribution behavior.

Technology Category

• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Intelligent Robots: Human-Robot Interaction
• Machine Learning: Privacy

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Assisted, interactive, and conversational search
• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems

Abstract

University research labs often rely on chat-based platforms for communication and project management, where valuable knowledge surfaces but is easily lost in message streams. Documentation can preserve knowledge, but it requires ongoing maintenance and is challenging to navigate. Drawing on formative interviews that revealed organizational memory challenges in labs, we designed CHOIR, an LLM-based chatbot that supports organizational memory through four key functions: document-grounded Q&A, Q&A sharing for follow-up discussion, knowledge extraction from conversations, and AI-assisted document updates. We deployed CHOIR in four research labs for one month (n=21), where the lab members asked 107 questions and lab directors updated documents 38 times in the organizational memory. Our findings reveal a privacy-awareness tension: questions were asked privately, limiting directors' visibility into documentation gaps. Students often avoided contribution due to challenges in generalizing personal experiences into universal documentation. We contribute design implications for privacy-preserving awareness and supporting context-specific knowledge documentation.

Problem

• University labs lose valuable knowledge in chat-based communication platforms
• Documentation requires ongoing maintenance and is difficult to navigate
• Organizational memory challenges limit knowledge preservation in research labs

Innovation

• LLM-based chatbot for organizational memory
• Document-grounded Q&A and knowledge extraction
• AI-assisted document updates from conversations