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

Antonios Anastasopoulos

ACL 2026×2评测与基准社会与人本多模态推理
新星分贡献者
32
一作贡献0
核心/参与10
方向广度8
合作网络3
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 #4/5ACL 2026Poster· Natural Language Processing

VIGNETTE : Socially Grounded Bias Evaluation for Vision-Language Models

Chahat Raj · Bowen Wei · Aylin Caliskan · Antonios Anastasopoulos · Ziwei Zhu

摘要

While bias in large language models (LLMs) is well-studied, similar concerns in vision-language models (VLMs) have received comparatively less attention. Existing VLM bias studies often focus on portrait-style images and gender-occupation associations, overlooking broader and more complex social...

多模态评测与基准社会与人本OpenReview 项目页
作者位次 #5/6ACL 2026Findings· Findings of ACL

Talent or Luck? Evaluating Attribution Bias in Large Language Models

Chahat Raj · Mahika Banerjee · Jinhao Pan · Aylin Caliskan · Antonios Anastasopoulos · Ziwei Zhu

摘要

When a student fails an exam, do we tend to blame their effort or the test’s difficulty? Attribution, defined as how reasons are assigned to event outcomes, shapes perceptions, reinforces stereotypes, and influences decisions. Attribution Theory explains how people attribute causes to internal fa...

社会与人本评测与基准推理OpenReview 项目页

常见合作者