一作ICML 2026Poster· Deep Learning / Large Language Models
PlugMem: A Task-Agnostic Plugin Memory Module for LLM Agents
Ke Yang · Zixi Chen · Xuan He · Jize Jiang · Michel Galley · Chenglong Wang · Jianfeng Gao · Jiawei Han · Chengxiang Zhai
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。
Ke Yang · Zixi Chen · Xuan He · Jize Jiang · Michel Galley · Chenglong Wang · Jianfeng Gao · Jiawei Han · Chengxiang Zhai
Saket Reddy · Ke Yang · ChengXiang Zhai
Mitigating social bias in Large Language Models (LLMs) presents a distinct alignment challenge: unlike verifiable tasks, social bias lacks a single ground truth, creating a high-variance, subjective reward landscape. Previous preference-based fine-tuning methods have major trade-offs: Direct Pref...