SafeScreen: A Safety-First Screening Framework for Personalized Video Retrieval for Vulnerable Users
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Question GenerationVideo RetrievalSimilar Papers 제목 키워드 기반
DPSCREEN: Dynamic Personalized Screening
Screening is important for the diagnosis and treatment of a wide variety of diseases. A good screening policy should be personalized to the disease, to the features of the patient and to the dynamic history of the pati…
Personalization Meets Safety:Mechanisms,Risks,and Mitigations in Personalized LLMs
Large Language Models (LLMs) have enabled increasingly personalized interactions by adapting to users' preferences, contexts, and long-term histories. However, the mechanisms that enable personalization also expand the s…
Reinforcement LearningWhen Personalization Legitimizes Risks: Uncovering Safety Vulnerabilities in Personalized Dialogue Agents
Long-term memory enables large language model (LLM) agents to support personalized and sustained interactions. However, most work on personalized agents prioritizes utility and user experience, treating memory as a neutr…
ConfidentCare: A Clinical Decision Support System for Personalized Breast Cancer Screening
Breast cancer screening policies attempt to achieve timely diagnosis by the regular screening of apparently healthy women. Various clinical decisions are needed to manage the screening process; those include: selecting t…
DiagnosticA Network Screening Method for Short-Term Safety Performance
Network screening is crucial to transportation safety management, enabling practitioners to identify high-risk locations and implement countermeasures to reduce crashes. Traditional methods focus on long-term crash trend…