Researchers have developed a retrieval-augmented chatbot called VideoPoints, designed to answer student questions using only course-specific lecture videos and provide timestamped citations. During a semester-long deployment, the chatbot successfully answered 70.5% of user queries with citations, declined to answer when no relevant lecture material was found, and improved lecture retrieval accuracy by 6.3 percentage points over standard methods. The study highlighted the importance of course isolation, citation support, and alignment with student study habits for effective deployment, with users identifying practice-question generation as a key unmet need. AI
IMPACT This research demonstrates a practical application of retrieval-augmented generation for educational purposes, potentially improving student study efficiency.
RANK_REASON The cluster contains a research paper detailing a new chatbot system and its evaluation.
Read on arXiv cs.IR (Information Retrieval) →
- EduVidQA
- VideoPoints
- alphaXiv
- arXiv
- CatalyzeX Code Finder for Papers
- Connected Papers
- CORE Recommender
- DagsHub
- Gotit.pub
- Hugging Face
- Influence Flower
- Litmaps
- ScienceCast
- scite Smart Citations
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →