Aylin Caliskan

87 papers A* 6A 1C 7Journal 48Unranked 25

Year	Rank	Type	Title / Venue / Authors
2026	A*	`conf`	A Framework to Characterize Reporting on Generative AI Use. CHI Agathe Balayn, Varun Nagaraj Rao, Su Lin Blodgett, Aylin Caliskan, Solon Barocas
2026	A*	`conf`	Identifying Features Associated with Bias Against 93 Stigmatized Groups in Language Models and Guardrail Model Safety Mitigation. AAAI Anna-Maria Gueorguieva, Aylin Caliskan
2026	J	`jnl`	VEAT Quantifies Implicit Associations in Text-to-Video Generator Sora and Reveals Challenges in Bias Mitigation. CoRR Yongxu Sun, Michael Saxon, Ian Yang, Anna-Maria Gueorguieva, Aylin Caliskan
2025	J	`jnl`	Beyond One-Way Influence: Bidirectional Opinion Dynamics in Multi-Turn Human-LLM Interactions. CoRR Yuyang Jiang, Longjie Guo, Yuchen Wu, Aylin Caliskan, Tanu Mitra, Hua Shen
2025	J	`jnl`	Bias Amplification in Stable Diffusion's Representation of Stigma Through Skin Tones and Their Homogeneity. CoRR Kyra Wilson, Sourojit Ghosh, Aylin Caliskan
2025	—	`conf`	Biases Propagate in Encoder-based Vision-Language Models: A Systematic Analysis From Intrinsic Measures to Zero-shot Retrieval Outcomes. ACL (Findings) Kshitish Ghate, Tessa Charlesworth, Mona T. Diab, Aylin Caliskan
2025	J	`jnl`	Biases Propagate in Encoder-based Vision-Language Models: A Systematic Analysis From Intrinsic Measures to Zero-shot Retrieval Outcomes. CoRR Kshitish Ghate, Tessa Charlesworth, Mona T. Diab, Aylin Caliskan
2025	J	`jnl`	EVALUESTEER: Measuring Reward Model Steerability Towards Values and Preferences. CoRR Kshitish Ghate, Andy Liu, Devansh Jain, Taylor Sorensen, Atoosa Kasirzadeh, Aylin Caliskan, Mona T. Diab, Maarten Sap
2025	J	`jnl`	Identifying Features Associated with Bias Against 93 Stigmatized Groups in Language Models and Guardrail Model Safety Mitigation. CoRR Anna-Maria Gueorguieva, Aylin Caliskan
2025	—	`conf`	Intrinsic Bias is Predicted by Pretraining Data and Correlates with Downstream Performance in Vision-Language Encoders. NAACL (Long Papers) Kshitish Ghate, Isaac Slaughter, Kyra Wilson, Mona T. Diab, Aylin Caliskan
2025	J	`jnl`	Intrinsic Bias is Predicted by Pretraining Data and Correlates with Downstream Performance in Vision-Language Encoders. CoRR Kshitish Ghate, Isaac Slaughter, Kyra Wilson, Mona T. Diab, Aylin Caliskan
2025	J	`jnl`	No Thoughts Just AI: Biased LLM Hiring Recommendations Alter Human Decision Making and Limit Human Autonomy. CoRR Kyra Wilson, Mattea Sim, Anna-Maria Gueorguieva, Aylin Caliskan
2025	J	`jnl`	Persona-Assigned Large Language Models Exhibit Human-Like Motivated Reasoning. CoRR Saloni Dash, Amélie Reymond, Emma S. Spiro, Aylin Caliskan
2025	J	`jnl`	Personalized Safety in LLMs: A Benchmark and A Planning-Based Agent Approach. CoRR Yuchen Wu, Edward Sun, Kaijie Zhu, Jianxun Lian, José Hernández-Orallo, Aylin Caliskan, Jindong Wang
2025	J	`jnl`	Safeguarding human values: rethinking US law for generative AI's societal impacts. AI Ethics Inyoung Cheong, Aylin Caliskan, Tadayoshi Kohno
2025	J	`jnl`	Talent or Luck? Evaluating Attribution Bias in Large Language Models. CoRR Chahat Raj, Mahika Banerjee, Aylin Caliskan, Antonios Anastasopoulos, Ziwei Zhu
2025	J	`jnl`	VIGNETTE: Socially Grounded Bias Evaluation for Vision-Language Models. CoRR Chahat Raj, Bowen Wei, Aylin Caliskan, Antonios Anastasopoulos, Ziwei Zhu
2024	—	`conf`	"I Don't See Myself Represented Here at All": User Experiences of Stable Diffusion Outputs Containing Representational Harms across Gender Identities and Nationalities. AIES (1) Sourojit Ghosh, Nina Lutz, Aylin Caliskan
2024	J	`jnl`	"I don't see myself represented here at all": User Experiences of Stable Diffusion Outputs Containing Representational Harms across Gender Identities and Nationalities. CoRR Sourojit Ghosh, Nina Lutz, Aylin Caliskan
2024	J	`jnl`	A Taxonomy of Stereotype Content in Large Language Models. CoRR Gandalf Nicolas, Aylin Caliskan
2024	—	`conf`	BiasDora: Exploring Hidden Biased Associations in Vision-Language Models. EMNLP (Findings) Chahat Raj, Anjishnu Mukherjee, Aylin Caliskan, Antonios Anastasopoulos, Ziwei Zhu
2024	J	`jnl`	BiasDora: Exploring Hidden Biased Associations in Vision-Language Models. CoRR Chahat Raj, Anjishnu Mukherjee, Aylin Caliskan, Antonios Anastasopoulos, Ziwei Zhu
2024	—	`conf`	Breaking Bias, Building Bridges: Evaluation and Mitigation of Social Biases in LLMs via Contact Hypothesis. AIES (1) Chahat Raj, Anjishnu Mukherjee, Aylin Caliskan, Antonios Anastasopoulos, Ziwei Zhu
2024	J	`jnl`	Breaking Bias, Building Bridges: Evaluation and Mitigation of Social Biases in LLMs via Contact Hypothesis. CoRR Chahat Raj, Anjishnu Mukherjee, Aylin Caliskan, Antonios Anastasopoulos, Ziwei Zhu
2024	J	`jnl`	ChatGPT as Research Scientist: Probing GPT's Capabilities as a Research Librarian, Research Ethicist, Data Generator and Data Predictor. CoRR Steven A. Lehr, Aylin Caliskan, Suneragiri Liyanage, Mahzarin R. Banaji
2024	—	`conf`	Do Generative AI Models Output Harm while Representing Non-Western Cultures: Evidence from A Community-Centered Approach. AIES (1) Sourojit Ghosh, Pranav Narayanan Venkit, Sanjana Gautam, Shomir Wilson, Aylin Caliskan
2024	J	`jnl`	Do Generative AI Models Output Harm while Representing Non-Western Cultures: Evidence from A Community-Centered Approach. CoRR Sourojit Ghosh, Pranav Narayanan Venkit, Sanjana Gautam, Shomir Wilson, Aylin Caliskan
2024	—	`conf`	Gender, Race, and Intersectional Bias in Resume Screening via Language Model Retrieval. AIES (1) Kyra Wilson, Aylin Caliskan
2024	J	`jnl`	Gender, Race, and Intersectional Bias in Resume Screening via Language Model Retrieval. CoRR Kyra Wilson, Aylin Caliskan
2024	—	`conf`	Global Gallery: The Fine Art of Painting Culture Portraits through Multilingual Instruction Tuning. NAACL-HLT Anjishnu Mukherjee, Aylin Caliskan, Ziwei Zhu, Antonios Anastasopoulos
2024	A*	`conf`	Label-Efficient Group Robustness via Out-of-Distribution Concept Curation. CVPR Yiwei Yang, Anthony Z. Liu, Robert Wolfe, Aylin Caliskan, Bill Howe
2023	—	`conf`	'Person' == Light-skinned, Western Man, and Sexualization of Women of Color: Stereotypes in Stable Diffusion. EMNLP (Findings) Sourojit Ghosh, Aylin Caliskan
2023	J	`jnl`	'Person' == Light-skinned, Western Man, and Sexualization of Women of Color: Stereotypes in Stable Diffusion. CoRR Sourojit Ghosh, Aylin Caliskan
2023	A*	`conf`	Artificial Intelligence, Bias, and Ethics. IJCAI Aylin Caliskan
2023	—	`conf`	Bias Against 93 Stigmatized Groups in Masked Language Models and Downstream Sentiment Classification Tasks. FAccT Katelyn Mei, Sonia Fereidooni, Aylin Caliskan
2023	J	`jnl`	Bias Against 93 Stigmatized Groups in Masked Language Models and Downstream Sentiment Classification Tasks. CoRR Katelyn Xiaoying Mei, Sonia Fereidooni, Aylin Caliskan
2023	C	`conf`	ChatGPT Perpetuates Gender Bias in Machine Translation and Ignores Non-Gendered Pronouns: Findings across Bengali and Five other Low-Resource Languages. AIES Sourojit Ghosh, Aylin Caliskan
2023	J	`jnl`	ChatGPT Perpetuates Gender Bias in Machine Translation and Ignores Non-Gendered Pronouns: Findings across Bengali and Five other Low-Resource Languages. CoRR Sourojit Ghosh, Aylin Caliskan
2023	—	`conf`	Contrastive Language-Vision AI Models Pretrained on Web-Scraped Multimodal Data Exhibit Sexual Objectification Bias. FAccT Robert Wolfe, Yiwei Yang, Bill Howe, Aylin Caliskan
2023	—	`conf`	Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scale. FAccT Federico Bianchi, Pratyusha Kalluri, Esin Durmus, Faisal Ladhak, Myra Cheng, Debora Nozza, Tatsunori Hashimoto, Dan Jurafsky, James Zou, Aylin Caliskan
2023	C	`conf`	Evaluating Biased Attitude Associations of Language Models in an Intersectional Context. AIES Shiva Omrani Sabbaghi, Robert Wolfe, Aylin Caliskan
2023	J	`jnl`	Evaluating Biased Attitude Associations of Language Models in an Intersectional Context. CoRR Shiva Omrani Sabbaghi, Robert Wolfe, Aylin Caliskan
2023	J	`jnl`	Is the U.S. Legal System Ready for AI's Challenges to Human Values? CoRR Inyoung Cheong, Aylin Caliskan, Tadayoshi Kohno
2023	—	`conf`	Pre-trained Speech Processing Models Contain Human-Like Biases that Propagate to Speech Emotion Recognition. EMNLP (Findings) Isaac Slaughter, Craig Greenberg, Reva Schwartz, Aylin Caliskan
2023	J	`jnl`	Pre-trained Speech Processing Models Contain Human-Like Biases that Propagate to Speech Emotion Recognition. CoRR Isaac Slaughter, Craig Greenberg, Reva Schwartz, Aylin Caliskan
2023	J	`jnl`	Traversable Wormhole in f(Q) Gravity Using Conformal Symmetry. Symmetry Munsif Jan, Asifa Ashraf, Abdul Basit, Aylin Caliskan, Ertan Güdekli
2022	C	`conf`	American == White in Multimodal Language-and-Image AI. AIES Robert Wolfe, Aylin Caliskan
2022	J	`jnl`	American == White in Multimodal Language-and-Image AI. CoRR Robert Wolfe, Aylin Caliskan
2022	J	`jnl`	Contrastive Language-Vision AI Models Pretrained on Web-Scraped Multimodal Data Exhibit Sexual Objectification Bias. CoRR Robert Wolfe, Yiwei Yang, Bill Howe, Aylin Caliskan
2022	—	`conf`	Contrastive Visual Semantic Pretraining Magnifies the Semantics of Natural Language Representations. ACL (1) Robert Wolfe, Aylin Caliskan
2022	J	`jnl`	Contrastive Visual Semantic Pretraining Magnifies the Semantics of Natural Language Representations. CoRR Robert Wolfe, Aylin Caliskan
2022	—	`conf`	Detecting Emerging Associations and Behaviors With Regional and Diachronic Word Embeddings. ICSC Robert Wolfe, Aylin Caliskan
2022	J	`jnl`	Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scale. CoRR Federico Bianchi, Pratyusha Kalluri, Esin Durmus, Faisal Ladhak, Myra Cheng, Debora Nozza, Tatsunori Hashimoto, Dan Jurafsky, James Zou, Aylin Caliskan
2022	—	`conf`	Evidence for Hypodescent in Visual Semantic AI. FAccT Robert Wolfe, Mahzarin R. Banaji, Aylin Caliskan
2022	J	`jnl`	Evidence for Hypodescent in Visual Semantic AI. CoRR Robert Wolfe, Mahzarin R. Banaji, Aylin Caliskan
2022	C	`conf`	Gender Bias in Word Embeddings: A Comprehensive Analysis of Frequency, Syntax, and Semantics. AIES Aylin Caliskan, Pimparkar Parth Ajay, Tessa Charlesworth, Robert Wolfe, Mahzarin R. Banaji
2022	J	`jnl`	Gender Bias in Word Embeddings: A Comprehensive Analysis of Frequency, Syntax, and Semantics. CoRR Aylin Caliskan, Pimparkar Parth Ajay, Tessa Charlesworth, Robert Wolfe, Mahzarin R. Banaji
2022	J	`jnl`	Learning to Behave: Improving Covert Channel Security with Behavior-Based Designs. Proc. Priv. Enhancing Technol. Ryan Wails, Andrew Stange, Eliana Troper, Aylin Caliskan, Roger Dingledine, Rob Jansen, Micah Sherr
2022	—	`conf`	Markedness in Visual Semantic AI. FAccT Robert Wolfe, Aylin Caliskan
2022	J	`jnl`	Markedness in Visual Semantic AI. CoRR Robert Wolfe, Aylin Caliskan
2022	C	`conf`	Measuring Gender Bias in Word Embeddings of Gendered Languages Requires Disentangling Grammatical Gender Signals. AIES Shiva Omrani Sabbaghi, Aylin Caliskan
2022	J	`jnl`	Measuring Gender Bias in Word Embeddings of Gendered Languages Requires Disentangling Grammatical Gender Signals. CoRR Shiva Omrani Sabbaghi, Aylin Caliskan
2022	A*	`conf`	VAST: The Valence-Assessing Semantics Test for Contextualizing Language Models. AAAI Robert Wolfe, Aylin Caliskan
2022	J	`jnl`	VAST: The Valence-Assessing Semantics Test for Contextualizing Language Models. CoRR Robert Wolfe, Aylin Caliskan
2021	J	`jnl`	A set of distinct facial traits learned by machines is not predictive of appearance bias in the wild. AI Ethics Ryan Steed, Aylin Caliskan
2021	—	`conf`	Automatically Characterizing Targeted Information Operations Through Biases Present in Discourse on Twitter. ICSC Autumn Toney, Akshat Pandey, Wei Guo, David A. Broniatowski, Aylin Caliskan
2021	C	`conf`	Detecting Emergent Intersectional Biases: Contextualized Word Embeddings Contain a Distribution of Human-like Biases. AIES Wei Guo, Aylin Caliskan
2021	J	`jnl`	Digital transformation of traditional marketing business model in new industry era. J. Enterp. Inf. Manag. Aylin Caliskan, Yesim Deniz Ozkan-Ozen, Yucel Ozturkoglu
2021	C	`conf`	Disparate Impact of Artificial Intelligence Bias in Ridehailing Economy's Price Discrimination Algorithms. AIES Akshat Pandey, Aylin Caliskan
2021	—	`conf`	Image Representations Learned With Unsupervised Pre-Training Contain Human-like Biases. FAccT Ryan Steed, Aylin Caliskan
2021	—	`conf`	Low Frequency Names Exhibit Bias and Overfitting in Contextualizing Language Models. EMNLP (1) Robert Wolfe, Aylin Caliskan
2021	J	`jnl`	Low Frequency Names Exhibit Bias and Overfitting in Contextualizing Language Models. CoRR Robert Wolfe, Aylin Caliskan
2021	—	`conf`	ValNorm Quantifies Semantics to Reveal Consistent Valence Biases Across Languages and Over Centuries. EMNLP (1) Autumn Toney, Aylin Caliskan
2020	J	`jnl`	Detecting Emergent Intersectional Biases: Contextualized Word Embeddings Contain a Distribution of Human-like Biases. CoRR Wei Guo, Aylin Caliskan
2020	J	`jnl`	Image Representations Learned With Unsupervised Pre-Training Contain Human-like Biases. CoRR Ryan Steed, Aylin Caliskan
2020	J	`jnl`	Iterative Effect-Size Bias in Ridehailing: Measuring Social Bias in Dynamic Pricing of 100 Million Rides. CoRR Akshat Pandey, Aylin Caliskan
2020	J	`jnl`	Machines Learn Appearance Bias in Face Recognition. CoRR Ryan Steed, Aylin Caliskan
2020	J	`jnl`	Pro-Russian Biases in Anti-Chinese Tweets about the Novel Coronavirus. CoRR Autumn Toney, Akshat Pandey, Wei Guo, David A. Broniatowski, Aylin Caliskan
2020	J	`jnl`	ValNorm: A New Word Embedding Intrinsic Evaluation Method Reveals Valence Biases are Consistent Across Languages and Over Decades. CoRR Autumn Toney, Aylin Caliskan
2019	J	`jnl`	Can market indicators forecast the port throughput? Int. J. Data Min. Model. Manag. Aylin Caliskan, Burcu Karaöz
2019	J	`jnl`	Git Blame Who?: Stylistic Authorship Attribution of Small, Incomplete Source Code Fragments. Proc. Priv. Enhancing Technol. Edwin Dauber, Aylin Caliskan, Richard E. Harang, Gregory Shearer, Michael J. Weisman, Frederica Free-Nelson, Rachel Greenstadt
2018	—	`conf`	Git blame who?: stylistic authorship attribution of small, incomplete source code fragments. ICSE (Companion Volume) Edwin Dauber, Aylin Caliskan, Richard E. Harang, Rachel Greenstadt
2018	A*	`conf`	When Coding Style Survives Compilation: De-anonymizing Programmers from Executable Binaries. NDSS Aylin Caliskan, Fabian Yamaguchi, Edwin Dauber, Richard E. Harang, Konrad Rieck, Rachel Greenstadt, Arvind Narayanan
2017	—	`conf`	Beyond Big Data: What Can We Learn from AI Models?: Invited Keynote. AISec@CCS Aylin Caliskan
2013	—	`conf`	From Language to Family and Back: Native Language and Language Family Identification from English Text. HLT-NAACL Ariel Stolerman, Aylin Caliskan, Rachel Greenstadt
2012	—	`conf`	Translate Once, Translate Twice, Translate Thrice and Attribute: Identifying Authors and Machine Translation Tools in Translated Text. ICSC Aylin Caliskan, Rachel Greenstadt
2012	A	`conf`	Use Fewer Instances of the Letter "i": Toward Writing Style Anonymization. Privacy Enhancing Technologies Andrew W. E. McDonald, Sadia Afroz, Aylin Caliskan, Ariel Stolerman, Rachel Greenstadt