How Well do LLMs Assist Parents in Assessing Child Appropriateness of Videos?
Sabila Nawshin, Ashley Phoebe Ishoel, Arun Balaji Buduru, Apu Kapadia
摘要
Children’s entertainment has become increasingly digital, with much of it available on video-sharing platforms. Although traditional media such as movies and TV are manually curated for appropriateness, the sheer quantity of videos being uploaded online makes this approach impractical. Current automated techniques fail to capture the diversity in parental supervision caused by varying parental preferences, culture, and other factors, while also lacking the transparency and explainability necessary to build parental trust. This study seeks to evaluate LLM’s ability to assess the appropriateness of videos for children under the age of 7 in an explainable manner and its overall alignment with parental values. Our study shows that while LLMs are less effective at determining appropriateness themselves, they can provide beneficial descriptions of the videos and effectively aid in the parental decision-making process.
问问这篇 Paper
问问你的智能体。
Lune 读过与它相关的顶会 Paper,每个回答都会注明依据哪几篇。
相关 Paper
- Weighing Benefits and Harms: Parental Mediation on Social Video PlatformsRenkai Ma, Yao Li, Sunhye Bai, Yubo Kou 等CHI 2025 · 被引用 8 次
- YouthCare: Building a Personalized Collaborative Video Censorship Tool to Support Parent-Child Joint Media EngagementWenxin Zhao, Fangyu Yu, Peng Zhang, Hansu Gu 等CHI 2025 · 被引用 4 次
- "Pikachu would electrocute people who are misbehaving": Expert, Guardian and Child Perspectives on Automated Embodied Moderators for Safeguarding Children in Social Virtual RealityCristina Fiani, Robin Bretin, Shaun Alexander Macdonald, Mohamed Khamis 等CHI 2024 · 被引用 18 次
- eaSEL: Promoting Social-Emotional Learning and Parent-Child Interaction through AI-Mediated Content ConsumptionJocelyn J. Shen, Jennifer King Chen, Leah Findlater, Griffin Dietz SmithCHI 2025 · 被引用 23 次
- On the Automatic Generation and Simplification of Children's StoriesMaria R. Valentini, Jennifer Weber, Jesus Salcido, Téa Wright 等EMNLP 2023 · 被引用 7 次
