paper.dinq.meAI 与前沿科学顶会 · 学术新星雷达
登录 DINQ
返回新星榜
ZM

Zhengwu Ma

ACL 2026×2安全可解释性评测与基准推理多语言与语言学
新星分贡献者
45
一作贡献0
核心/参与17
方向广度10
合作网络6
0 一作 · 2 篇 · ACL 2026

获取完整研究档案

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。

联系方式

实时查找电子邮箱,费用不超过20积分;未找到邮箱不扣费。

2026 顶会论文

2
作者位次 #6/8ACL 2026Findings· Findings of ACL

Conflicts Make Large Reasoning Models Vulnerable to Attacks

Honghao Liu · Chengjin Xu · Xuhui Jiang · Cehao Yang · Shengming Yin · Zhengwu Ma · Lionel Ni · Jian Guo

摘要

Large Reasoning Models (LRMs) have achieved remarkable performance across diverse domains, yet their decision-making under conflicting objectives remains insufficiently understood. This work investigates how LRMs respond to harmful queries when confronted with two categories of conflicts: interna...

安全可解释性评测与基准OpenReview 项目页
作者位次 #2/8ACL 2026Findings· Findings of ACL

Traces in the Brain: Neural Evidence for Syntactic Movement in E nglish and C hinese

Yuhan Huang · Zhengwu Ma · Yuqi Jin · Beth Chan · Zheng Shen · Jackie Yan-Ki Lai · John T. Hale · Jixing Li

摘要

Syntactic movement is a core concept in generative linguistics to account for word-order variation and long-distance dependencies, but its psychological and neurobiological status remains debated. Here, we test the neural reality of movement in English and Chinese by correlating brain activity du...

推理多语言与语言学OpenReview 项目页

常见合作者