作者位次 #2/5NeurIPS 2026Poster
How Does Personalized Memory Shape LLM Behavior? Benchmarking Rational Preference Utilization in Personalized Assistants
Xueyang Feng · Weinan Gan · Xu Chen · Quanyu Dai · Yong Liu
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。
Xueyang Feng · Weinan Gan · Xu Chen · Quanyu Dai · Yong Liu
Song-Li Wu · Zhaocheng Du · Weinan Gan · Jingyi Wang · Xianquan Wang
Recent studies indicate a fundamental incompatibility between ID representations and language model (LM) representations, as they capture behavioral and semantic spaces respectively. This mismatch leads LM representations to consistently underperform ID representations in recommendation tasks. In...
Yingyi Zhang · an Jiaotong University) · Derong Xu · Yi Wen · Xianneng Li · Yichao Wang · Wenlin Zhang · Xiaopeng Li · Weinan Gan · Huifeng Guo · Yong Liu · an Jiaotong University)
Ziyi Zhao · Chongming Gao · Yang Zhang · Haoyan Liu · Weinan Gan · Huifeng Guo · Yong Liu · Fuli Feng