作者位次 #2/4ICLR 2026Oral
Beyond Prompt-Induced Lies: Investigating LLM Deception on Benign Prompts
Zhaomin Wu · Mingzhe Du · See-Kiong Ng · Bingsheng He
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。
Zhaomin Wu · Mingzhe Du · See-Kiong Ng · Bingsheng He
Chengran Yang · Ting Zhang · Jinfeng Jiang · Xin Zhou · Haoye Tian · Mingzhe Du · Jieke Shi · Junkai Chen · Yikun Li · Eng Lieh Ouh · Lwin Khin Shar · David Lo
The rapid accumulation of software vulnerabilities has outpaced manual remediation, creating an urgent need for Automated Vulnerability Repair (AVR). However, existing methods suffer from syntactic overfitting, mimicking surface forms without understanding the underlying repair logic, and fail to...