Aylin Caliskan
15 papers · 2013–2026 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+7 more ↓ Show less ↑
π Interdisciplinary Bridge π Academic Marathon (12) π Conference Polyglot (6) π Renaissance Researcher (7) πΊοΈ Taxonomy Completionist (33)
π
Interdisciplinary Bridge
π£
Hot Topic Early Bird
πΊοΈ
Taxonomy Completionist
(33)
π§¬
Topic Evolution
ποΈ
Keyword Collector
(77)
π
Century Club
(13)
π₯
Unstoppable
(5)
Conferences
EMNLP (5)
ACL (3)
NAACL (3)
AAAI (2)
CVPR (1)
IJCAI (1)
Top co-authors
Keywords
social bia
(5)
vision-language model
(5)
bias detection
(3)
language model
(3)
gender bia
(3)
bias mitigation
(2)
semantic analysis
(2)
racial bia
(2)
intrinsic evaluation
(2)
speech processing
(1)
text-to-image generation
(1)
multilingual nlp
(1)
semantic representation
(1)
instruction tuning
(1)
zero-shot learning
(1)
text representation
(1)
visual question answering
(1)
generative model
(1)
multimodal learning
(1)
distributionally robust optimization
(1)
Papers
Identifying Features Associated with Bias Against 93 Stigmatized Groups in Language Models and Guardrail Model Safety Mitigation
AAAI 2026
VIGNETTE: Socially Grounded Bias Evaluation for Vision-Language Models
ACL 2026
Intrinsic Bias is Predicted by Pretraining Data and Correlates with Downstream Performance in Vision-Language Encoders
NAACL 2025
Biases Propagate in Encoder-based Vision-Language Models: A Systematic Analysis From Intrinsic Measures to Zero-shot Retrieval Outcomes
ACL 2025
Label-Efficient Group Robustness via Out-of-Distribution Concept Curation
CVPR 2024
BiasDora: Exploring Hidden Biased Associations in Vision-Language Models
EMNLP 2024
Global Gallery: The Fine Art of Painting Culture Portraits through Multilingual Instruction Tuning
NAACL 2024
Pre-trained Speech Processing Models Contain Human-Like Biases that Propagate to Speech Emotion Recognition
EMNLP 2023
βPersonβ == Light-skinned, Western Man, and Sexualization of Women of Color: Stereotypes in Stable Diffusion
EMNLP 2023
Artificial Intelligence, Bias, and Ethics
IJCAI 2023
VAST: The Valence-Assessing Semantics Test for Contextualizing Language Models
AAAI 2022
Contrastive Visual Semantic Pretraining Magnifies the Semantics of Natural Language Representations
ACL 2022
ValNorm Quantifies Semantics to Reveal Consistent Valence Biases Across Languages and Over Centuries
EMNLP 2021
Low Frequency Names Exhibit Bias and Overfitting in Contextualizing Language Models
EMNLP 2021
From Language to Family and Back: Native Language and Language Family Identification from English Text
NAACL 2013