CHOIR: A Chatbot-mediated Organizational Memory Leveraging Communication in University Research Labs
Sangwook Lee, Adnan Abbas, Yan Chen, Young-Ho Kim, Sang Won Lee
ACM CHI 2026 (Under Review)

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.

CHOIR System Overview

Key Features

CHOIR provides four main functions to support organizational memory in research labs:

  1. Document-grounded Q&A: Lab members can ask questions and receive answers grounded in the lab's documentation.
  2. Q&A Sharing for Follow-up Discussion: Questions and answers can be shared for further discussion and knowledge refinement.
  3. Knowledge Extraction from Conversations: The system extracts valuable knowledge from ongoing conversations.
  4. AI-assisted Document Updates: Lab directors can update documentation with AI assistance based on accumulated Q&A interactions.

Deployment Study

We deployed CHOIR in four university research labs for one month with 21 participants. During the deployment:

  • Lab members asked 107 questions using the chatbot
  • Lab directors updated documents 38 times in the organizational memory
  • Our findings revealed important tensions between privacy and awareness in knowledge sharing

Design Implications

Our study contributes design implications for:

  • Privacy-preserving awareness: Balancing individual privacy needs with organizational visibility
  • Context-specific knowledge documentation: Supporting the generalization of personal experiences into universal documentation