Researcher — paper.dinq.me

作者位次 #6/6NeurIPS 2026Poster

Illusory Pattern Perception Drives Spurious Inference in Large Language Models

Peihua Mai · Zhuoyan Shao · Xinbao Qiao · Meng Zhang · Xinyue Zhou · Yan Pang

作者位次 #6/6ACL 2026Poster· Natural Language Processing

S hared R equest: Privacy-Preserving Model-Agnostic Inference for Large Language Models

Peihua Mai · Xuanrong Gao · Youlong Ding · Xianglong Du · Wei Liu · Yan Pang

摘要

With the widespread deployment of public large language models (LLMs) such as ChatGPT, protecting user prompt privacy has become an increasingly critical issue. Existing privacy-preserving inference methods sacrifice either utility or efficiency, and often require model-specific modifications tha...

效率与系统安全可解释性OpenReview 项目页

Yan Pang

获取完整研究档案

联系方式

2026 顶会论文

Illusory Pattern Perception Drives Spurious Inference in Large Language Models

S hared R equest: Privacy-Preserving Model-Agnostic Inference for Large Language Models

常见合作者