一作ICML 2026Poster· Social Aspects / Robustness
BESplit: Bias-Compensated Split Federated Learning with Evidential Aggregation
Yuhan Xie · Chen Lyu · Jingrong Huang
社会与人本OpenReview
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。
Yuhan Xie · Chen Lyu · Jingrong Huang
Yuhan Xie · Chen Lyu
Yutao Hou · Yihan Jiang · Yuhan Xie · Jian Yang · Liwen Zhang · Hailiang Huang · Guanhua Chen · Yun Chen
Large language models (LLMs) are increasingly applied in financial scenarios. However, they may produce harmful outputs, including facilitating illegal activities or unethical behavior, posing serious compliance risks. To systematically evaluate LLM safety in finance, we propose FinSafetyBench, a...
Yuhan Xie · Chen Lyu