Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.26918 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916049716248576 |
|---|---|
| author | Lee, Unggi Ahn, Hoyoung Choi, Yoon Eun, Seonmin Jeong, Jahyun Jin, Seonmin Jung, Harmony Kim, Hye Jin Lee, Chaerin Lee, Hyunji Lee, Jeongjin Lee, Soohwan Oh, Young-Seok Park, Jaehyeon Ryu, Sun-ok Shin, Sunyoung Son, Yoorim Park, Haeun Jeong, Yeil |
| author_facet | Lee, Unggi Ahn, Hoyoung Choi, Yoon Eun, Seonmin Jeong, Jahyun Jin, Seonmin Jung, Harmony Kim, Hye Jin Lee, Chaerin Lee, Hyunji Lee, Jeongjin Lee, Soohwan Oh, Young-Seok Park, Jaehyeon Ryu, Sun-ok Shin, Sunyoung Son, Yoorim Park, Haeun Jeong, Yeil |
| contents | Video generation models (VGMs) are rapidly entering classrooms, yet existing benchmarks evaluate only perceptual quality, intrinsic faithfulness, generic safety, or video as a reasoning medium, and none assesses whether the outputs are educationally valid. In this work, we present EduVideoBench, the first balanced benchmark in the education domain, grounded in the Knowledge-Skills-Attitude (KSA) framework so that pedagogical adequacy and educational safety are evaluated jointly rather than as ad-hoc quality dimensions. Across five frontier VGMs, our results show substantial room for improvement across knowledge, skills, and attitude before they are classroom-ready. We complement this with a qualitative analysis of expert comments, finding that educational validity is multi-component, where a single misaligned element such as pacing, legibility, or notation can invalidate an otherwise correct video. We hope EduVideoBench will guide the development of VGMs that are pedagogically grounded and safe for the classroom. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_26918 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Are Video Models Zero-Shot Learners and Reasoners in Education? EduVideoBench, A Knowledge-Skills-Attitude Benchmark for Educational Video Generation Lee, Unggi Ahn, Hoyoung Choi, Yoon Eun, Seonmin Jeong, Jahyun Jin, Seonmin Jung, Harmony Kim, Hye Jin Lee, Chaerin Lee, Hyunji Lee, Jeongjin Lee, Soohwan Oh, Young-Seok Park, Jaehyeon Ryu, Sun-ok Shin, Sunyoung Son, Yoorim Park, Haeun Jeong, Yeil Computation and Language Video generation models (VGMs) are rapidly entering classrooms, yet existing benchmarks evaluate only perceptual quality, intrinsic faithfulness, generic safety, or video as a reasoning medium, and none assesses whether the outputs are educationally valid. In this work, we present EduVideoBench, the first balanced benchmark in the education domain, grounded in the Knowledge-Skills-Attitude (KSA) framework so that pedagogical adequacy and educational safety are evaluated jointly rather than as ad-hoc quality dimensions. Across five frontier VGMs, our results show substantial room for improvement across knowledge, skills, and attitude before they are classroom-ready. We complement this with a qualitative analysis of expert comments, finding that educational validity is multi-component, where a single misaligned element such as pacing, legibility, or notation can invalidate an otherwise correct video. We hope EduVideoBench will guide the development of VGMs that are pedagogically grounded and safe for the classroom. |
| title | Are Video Models Zero-Shot Learners and Reasoners in Education? EduVideoBench, A Knowledge-Skills-Attitude Benchmark for Educational Video Generation |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2605.26918 |