为脆弱用户设计安全优先的个性化视频筛选系统，防止不当内容暴露。
SafeScreen: A Safety-First Screening Framework for Personalized Video Retrieval for Vulnerable Users
- 以安全为前提，逐条审查候选视频，不依赖预标注标签。
- 在痴呆照护场景中，80%-93%情况下优于主流推荐算法的安全性。
- 结合用户画像与多模态分析，实现可解释的实时内容筛选，适合医疗照护等敏感场景。
开放域视频平台虽能提供丰富个性化内容，支持健康、照护和教育应用，但其以参与度为导向的推荐算法可能使脆弱用户暴露于不当或有害内容。此类风险在儿童导向及照护场景（如阿尔茨海默病照护）中尤为突出，内容必须满足个体化安全约束方可展示。我们提出SafeScreen，一种以安全为先的视频筛选框架，可在保证个性化的同时强制执行个体化安全约束。该框架不以相关性或热度排序视频，而是通过自动化流水线对候选视频进行逐项批准或拒绝。其包含三个核心组件：(i) 基于用户画像提取个体化安全标准；(ii) 通过自适应提问生成与多模态VideoRAG分析进行证据驱动评估；(iii) 利用大语言模型验证安全性、适宜性与相关性后再决定内容呈现。该设计实现了无需预标注标签的可解释、实时未编目视频库筛查。我们在使用30个合成患者画像和90个测试查询的痴呆照护回忆案例中评估SafeScreen。结果表明，其在80%-93%情况下将安全置于参与度之上，显著偏离YouTube的优化排名，同时保持高安全覆盖率、合理性和依据性，经大模型评估与领域专家验证均获认可。
原文摘要 · Abstract (English)
Open-domain video platforms offer rich, personalized content that could support health, caregiving, and educational applications, but their engagement-optimized recommendation algorithms can expose vulnerable users to inappropriate or harmful material. These risks are especially acute in child-directed and care settings (e.g., dementia care), where content must satisfy individualized safety constraints before being shown. We introduce SafeScreen, a safety-first video screening framework that retrieves and presents personalized video while enforcing individualized safety constraints. Rather than ranking videos by relevance or popularity, SafeScreen treats safety as a prerequisite and performs sequential approval or rejection of candidate videos through an automated pipeline. SafeScreen integrates three key components: (i) profile-driven extraction of individualized safety criteria, (ii) evidence-grounded assessments via adaptive question generation and multimodal VideoRAG analysis, and (iii) LLM-based decision-making that verifies safety, appropriateness, and relevance before content exposure. This design enables explainable, real-time screening of uncurated video repositories without relying on precomputed safety labels. We evaluate SafeScreen in a dementia-care reminiscence case study using 30 synthetic patient profiles and 90 test queries. Results demonstrate that SafeScreen prioritizes safety over engagement, diverging from YouTube's engagement-optimized rankings in 80-93% of cases, while maintaining high levels of safety coverage, sensibleness, and groundedness, as validated by both LLM-based evaluation and domain experts.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。