作者位次 #2/4ICML 2026Spotlight· Social Aspects / Alignment
Toward Stable Value Alignment: Introducing Independent Modules for Consistent Value Guidance
Wenhao Chen · Sirui Sun · Shengyuan Bai · Guojie Song
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。
Wenhao Chen · Sirui Sun · Shengyuan Bai · Guojie Song
TianZe Zhang · Sirui Sun · Yuhang Xie · Xin Zhang · Zhiqiang Wu · Guojie Song
Large Language Models (LLMs) have shown promise in simulating human behavior, yet existing agents often exhibit behavioral rigidity, a flaw frequently masked by the self-referential bias of current “LLM-as-a-judge” evaluations. By evaluating against empirical ground truth, we reveal a counter-int...