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

Pengyun Zhu

ACL 2026×2数据与预训练安全可解释性推理对齐与偏好
新星分新星
75
一作贡献60
核心/参与0
方向广度10
合作网络6
2 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
一作ACL 2026Poster· Natural Language Processing

APPSI -139: A Parallel Corpus of E nglish Application Privacy Policy Summarization and Interpretation

Pengyun Zhu · Qiheng Sun · Long Wen · Yanbo Wang · YANG CAO · Junxu Liu · Deyi Xiong · Jinfei Liu · Zhibo Wang · Kui Ren

摘要

Privacy policies are essential for users to understand how service providers handle their personal data. However, these documents are often long and complex, as well as filled with technobabble and legalese, causing users to unknowingly accept terms that may even contradict the law. While summari...

数据与预训练安全可解释性OpenReview 项目页
一作ACL 2026Poster· Natural Language Processing

DVM ap: Fine-Grained Pluralistic Value Alignment via High-Consensus Demographic-Value Mapping

Pengyun Zhu · Yuqi Ren · Zhen Wang · Lei Yang · Deyi Xiong

摘要

Current Large Language Models (LLMs) typically rely on coarse-grained national labels for pluralistic value alignment. However, such macro-level supervision often obscures intra-country value heterogeneity, yielding a loose alignment.We argue that resolving this limitation requires shifting from...

推理对齐与偏好强化学习与后训练OpenReview 项目页

常见合作者