一作ICLR 2026Poster· Social Aspects / Fairness, Equity, Justice and Safety
Bi-directional Bias Attribution: Debiasing Large Language Models without Modifying Prompts
Yujie Lin · Kunquan Li · YiXuan Liao · Xiaoxin Chen · Jinsong Su
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。
Yujie Lin · Kunquan Li · YiXuan Liao · Xiaoxin Chen · Jinsong Su
Guoqi Ma · Liang Zhang · Hongyao Tu · Hao Fu · Hui Li · Yujie Lin · Longyue Wang · Weihua Luo · Jinsong Su
Cross-document relation extraction (RE) aims to identify relations between the head and tail entities located in different documents. Existing approaches typically adopt the paradigm of “ Small Language Model (SLM) + Classifier ”. However, the limited language understanding ability of SLMs hinder...
Ante Wang · Yujie Lin · Jingyao Liu · Suhang Wu · Hao Liu · Xinyan Xiao · Jinsong Su