الباحثون

Jing Tan

المنشورات 2

نسخة أولية وصول مفتوح

Raising the Bar for Chinese Adolescent LLM Safety: A Culturally-Grounded, Fine-Grained Benchmark

Jinxiang Wang, Yifan Liu, Jing Tan وآخرون · 2026

Safety risks in conversations with adolescents are not always explicit. A request may appear harmless unless a model considers the user's age, circumstances, and earlier turns. Existing Chinese safety benchmarks mainly target general users and give limited attention to adolescent safety. Single-turn tests also miss ris …

نسخة أولية وصول مفتوح

SaplingGuard: A Multidimensional-Profile-Aware Multi-Agent Guardrail for Developmentally Safe Adolescent-LLM Interaction

Jing Tan, Yifan Liu, Yi Lin وآخرون · 2026

As adolescents increasingly use LLMs in everyday life, ensuring safe and developmentally appropriate responses has become essential. However, existing LLM guardrails primarily target explicit harmful content in isolated prompts or responses and are less effective at identifying implicit, context-dependent developmental …

المؤلفون المشاركون