AskNow: An LLM-powered Interactive System for Real-Time Question Answering in Large-Scale Classrooms

2025-11-03

AI Summary

To address students’ reluctance to ask questions in large-scale classrooms—stemming from cognitive overload and social anxiety—this paper proposes a context-aware real-time Q&A system powered by large language models (LLMs). The system dynamically fuses multimodal classroom contexts—including lecture slides, handwritten notes, and speech transcripts—during instruction, enabling anonymous, instant student queries and generating precise, context-grounded answers. It further introduces a bidirectional pedagogical dashboard that aggregates frequent misconceptions and knowledge gaps for instructors. Key innovations include: (i) a lightweight context modeling mechanism ensuring sub-second response latency, and (ii) a dual-objective interaction design balancing student privacy preservation with actionable instructor feedback. Empirical evaluation across three university courses demonstrates a 62% reduction in average query resolution time and 91.3% instructor satisfaction with answer accuracy, significantly enhancing interactivity and learning experience in large-enrollment settings.

Technology Category

• Natural Language Processing: Question Answering
• Machine Learning: Large Multimodal Models (LMMs)
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

In large-scale classrooms, students often struggle to ask questions due to limited instructor attention and social pressure. Based on findings from a formative study with 24 students and 12 instructors, we designed AskNow, an LLM-powered system that enables students to ask questions and receive real-time, context-aware responses grounded in the ongoing lecture and that allows instructors to view students' questions collectively. We deployed AskNow in three university computer science courses and tested with 117 students. To evaluate AskNow's responses, each instructor rated the perceived correctness and satisfaction of 100 randomly sampled AskNow-generated responses. In addition, we conducted interviews with 24 students and the three instructors to understand their experience with AskNow. We found that AskNow significantly reduced students' perceived time to resolve confusion. Instructors rated AskNow's responses as highly accurate and satisfactory. Instructor and student feedback provided insights into supporting real-time learning in large lecture settings.

Problem

• Addresses limited instructor attention in large classrooms
• Reduces social pressure for students asking questions
• Provides real-time context-aware answers during lectures

Innovation

• LLM-powered real-time Q&A system for classrooms
• Context-aware responses based on ongoing lecture content
• Collective question viewing interface for instructors