# Context Selection and Rewriting for Video-based Educational Question Generation

arXiv: https://arxiv.org/abs/2504.19406 · HTML: https://mlsanity.com/paper/2504.19406/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 34 references that are in the map.
- First posted on arXiv 28 Apr 2025.

## Builds on (most cited first, 18 of 18)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Large Language Models Can Be Easily Distracted by Irrelevant Context](https://mlsanity.com/paper/2302.00093/) (2023)
- [Fantastic Questions and Where to Find Them: FairytaleQA -- An Authentic Dataset for Narrative Comprehension](https://mlsanity.com/paper/2203.13947/) (2022)
- [How Easily do Irrelevant Inputs Skew the Responses of Large Language Models?](https://mlsanity.com/paper/2404.03302/) (2024)
- [On the Evaluation Metrics for Paraphrase Generation](https://mlsanity.com/paper/2202.08479/) (2022)
- [Not All Contexts Are Equal: Teaching LLMs Credibility-aware Generation](https://mlsanity.com/paper/2404.06809/) (2024)
- [Question Generation for Reading Comprehension Assessment by Modeling How and What to Ask](https://mlsanity.com/paper/2204.02908/) (2022)
- [Learning to Generate Questions by Learning What not to Generate](https://mlsanity.com/paper/1902.10418/) (2019)
- [RQUGE: Reference-Free Metric for Evaluating Question Generation by Answering the Question](https://mlsanity.com/paper/2211.01482/) (2022)
- [EduQG: A Multi-format Multiple Choice Dataset for the Educational Domain](https://mlsanity.com/paper/2210.06104/) (2022)
- [Improving Question Generation with Multi-level Content Planning](https://mlsanity.com/paper/2310.13512/) (2023)
- [Savaal: Scalable Concept-Driven Question Generation to Enhance Human Learning](https://mlsanity.com/paper/2502.12477/) (2025)
- [Exploring Contrast Consistency of Open-Domain Question Answering Systems on Minimally Edited Questions](https://mlsanity.com/paper/2305.14441/) (2023)
- [SkillQG: Learning to Generate Question for Reading Comprehension Assessment](https://mlsanity.com/paper/2305.04737/) (2023)

## Built on by (most cited first, 1 of 1)

- [Beyond Factual QA: Mentorship-Oriented Question Answering over Long-Form Multilingual Content](https://mlsanity.com/paper/2601.17173/) (2026)

## Abstract (arXiv)

Educational question generation (EQG) is a crucial component of intelligent educational systems, significantly aiding self-assessment, active learning, and personalized education. While EQG systems have emerged, existing datasets typically rely on predefined, carefully edited texts, failing to represent real-world classroom content, including lecture speech with a set of complementary slides. To bridge this gap, we collect a dataset of educational questions based on lectures from real-world classrooms. On this realistic dataset, we find that current methods for EQG struggle with accurately generating questions from educational videos, particularly in aligning with specific timestamps and target answers. Common challenges include selecting informative contexts from extensive transcripts and ensuring generated questions meaningfully incorporate the target answer. To address the challenges, we introduce a novel framework utilizing large language models for dynamically selecting and rewriting contexts based on target timestamps and answers. First, our framework selects contexts from both lecture transcripts and video keyframes based on answer relevance and temporal proximity. Then, we integrate the contexts selected from both modalities and rewrite them into answer-containing knowledge statements, to enhance the logical connection between the contexts and the desired answer. This approach significantly improves the quality and relevance of the generated questions. Our dataset and code are released in https://github.com/mengxiayu/COSER.