Researcher — paper.dinq.me

2026 顶会论文

作者位次 #2/4ICLR 2026Poster· Social Aspects / Fairness, Equity, Justice and Safety

NDAD: Negative-Direction Aware Decoding for Large Language Models via Controllable Hallucination Signal Injection

Panjia Qiu · Mingyuan Fan · Cen Chen · Daixin Wang

安全社会与人本代码OpenReview

作者位次 #4/5ACL 2026Findings· Findings of ACL

M ed C oach: Enhancing Medical Reasoning in LLM s via Knowledge Graph-Augmented Chain-of-Thought Distillation

Chuan Li · Ye Lyu · Chengyu Wang · Mingyuan Fan · Cen Chen

摘要

Despite the advanced capabilities of Large Language Models (LLMs), training specialized reasoning models for the medical domain remains a significant challenge due to the scarcity of high-quality, large-scale Chain-of-Thought (CoT) data. Moreover, the intermediate reasoning steps in teacher-gener...

推理检索与知识可解释性OpenReview 项目页

一作CCS 2026Oral· Computer & Communications Security

What Does the Server See- Understanding Privacy Leakage from Large Language Models in Split Inference

Mingyuan Fan · Yu Liu · Fuyi Wang · Cen Chen

安全效率与系统OpenReview

Mingyuan Fan

获取完整研究档案

联系方式

2026 顶会论文

NDAD: Negative-Direction Aware Decoding for Large Language Models via Controllable Hallucination Signal Injection

M ed C oach: Enhancing Medical Reasoning in LLM s via Knowledge Graph-Augmented Chain-of-Thought Distillation

What Does the Server See- Understanding Privacy Leakage from Large Language Models in Split Inference

常见合作者