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

Max Upravitelev

ACL 2026×2强化学习与后训练数据与预训练可解释性评测与基准推理
新星分贡献者
38
一作贡献0
核心/参与10
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 #5/10ACL 2026Poster· Natural Language Processing

Uncovering Temporal Framing in the News

Tarek Mahmoud · Veronika Solopova · Premtim Sahitaj · Ariana Sahitaj · Max Upravitelev · Mervat Abassy · Hana Fatima Shaikh · Neda Foroutan · Vera Schmitt · Preslav Nakov

摘要

Temporal language does more than place events on a timeline. In news discourse, references to the past, present, and future can function as rhetorical devices that shape interpretation and persuasion. Here, we study temporal framing , defined as the persuasive use of time-related language to stru...

数据与预训练可解释性强化学习与后训练OpenReview 项目页
作者位次 #3/9ACL 2026Findings· Findings of ACL

Fine-tuning with Hierarchical Prompting for Robust Propaganda Classification Across Annotation Schemas

Lukas Stähelin · Veronika Solopova · Max Upravitelev · David Kaplan · Premtim Sahitaj · Ariana Sahitaj · Charlott Jakob · Sebastian Möller · Vera Schmitt

摘要

Propaganda detection in social media is challenging due to noisy, short texts and low annotation agreements. We introduce a new intent-focused taxonomy of propaganda techniques and compare it against an established, higher-agreement schema. Along three dimensions (model portfolio, schema effects,...

评测与基准推理强化学习与后训练OpenReview 项目页

常见合作者