作者位次 #2/4ICLR 2026Poster· Applications / Everything Else
Token-Efficient Long-Term Interest Sketching and Internalized Reasoning for LLM-based Recommendation
Zhihao Ding · Jinming Li · Shuai Mu · Jieming Shi
首次获取该候选人的完整档案及 StartLux 评估共 20 积分；每位用户单独解锁，之后查看免费。主动刷新 20 积分。
实时查找电子邮箱，费用不超过20积分；未找到邮箱不扣费。
Zhihao Ding · Jinming Li · Shuai Mu · Jieming Shi
Zhihao Ding · Jinming Li · Ze Lu · Jieming Shi
Ensuring the safety of LLM-generated content is essential for real-world deployment. Most existing guardrail models formulate moderation as a fixed binary classification task, implicitly assuming a fixed definition of harmfulness. In practice, enforcement strictness—how conservatively harmfulness...