# Cite or Decline: A Strict Course-Grounded Chatbot for STEM Lecture Videos

arXiv: https://arxiv.org/abs/2609.01846 · HTML: https://mlsanity.com/paper/2609.01846/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 18 references that are in the map.
- First posted on arXiv 1 Sep 2026.

## Builds on (most cited first, 7 of 7)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Jill Watson: A Virtual Teaching Assistant powered by ChatGPT](https://mlsanity.com/paper/2405.11070/) (2024)
- [SyllabusQA: A Course Logistics Question Answering Dataset](https://mlsanity.com/paper/2403.14666/) (2024)
- [EduVidQA: Generating and Evaluating Long-form Answers to Student Questions based on Lecture Videos](https://mlsanity.com/paper/2509.24120/) (2025)
- [Visual Summarization of Lecture Video Segments for Enhanced Navigation](https://mlsanity.com/paper/2006.02434/) (2020)
- [Visual Content Detection in Educational Videos with Transfer Learning and Dataset Enrichment](https://mlsanity.com/paper/2506.21903/) (2025)

## Abstract (arXiv)

Recorded lecture videos, often enhanced with search and summarization features, are a standard study resource. However, students cannot easily ask course specific questions or verify answers against an instructor's lecture. We report a semester-long deployment of VideoPoints platform with a retrieval-augmented chatbot that answers from course lecture materials and returns timestamped citations. The chatbot retrieves only from the active course, uses chapter summaries to guide transcript ranking, and returns clickable timestamped citations. Students used it for quick lookups and exam review. Across 833 messages, 70.5% included citations, none crossed a course boundary, and when no lecture evidence matched, the chatbot usually declined rather than answering. Among the users, citations were the most consistently useful feature, while practice-question generation was the strongest unmet request. We also evaluated the design on the real-world test split of EduVidQA, a public multimodal benchmark for lecture-video question answering. Our design improved correct-lecture retrieval by 6.3 percentage points over dense-only retrieval. Together, the results show that effective deployment depends on course isolation, supported citations, and alignment with students' study practices.