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

Lingwei Wei

ACL 2026KDD 2026SIGIR 2026对齐与偏好可解释性评测与基准推理安全
新星分新星
82
一作贡献40
核心/参与28
方向广度16
合作网络9
1 一作 · 3 篇 · ACL 2026 / KDD 2026 / SIGIR 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

3
作者位次 #2/5ACL 2026Poster· Natural Language Processing

Multi-Task Representation Alignment on Language Understanding: A Mutual Information Perspective

Dou Hu · Lingwei Wei · Hongjiang Xiao · Songlin Hu · Yuan Zhang

摘要

Multi-task learning (MTL) enables joint learning over multiple tasks based on shared representations, but suffers from task interference issue during optimization. Existing works mainly focus on task balancing or probabilistic modeling but fail to address the issue since they struggle to learn su...

对齐与偏好可解释性评测与基准OpenReview 项目页
作者位次 #2/4SIGIR 2026Oral· Information Retrieval (Full)

Mitigating Adversarial Attacks by Transferring LLM-generated Narrative Reasoning for Robust Fake News Detection

Mengyang Chen · Lingwei Wei · Wei Zhou · Songlin Hu

摘要

Propagation-based fake news detectors primarily extract structural patterns from news propagation trees via graph neural networks (GNNs), which are crucial for trustworthy information access on social platforms. However, these systems remain vulnerable to adversarial message injection, increasing...

推理安全对齐与偏好OpenReview

常见合作者