Ninareh Mehrabi

51 papers A* 5B 1Journal 33Unranked 12

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	FERRET: Framework for Expansion Reliant Red Teaming. CoRR Ninareh Mehrabi, Vitor Albiero, Maya Pavlova, Joanna Bitton
2026	J	`jnl`	Robust Persona-Aware Toxicity Detection with Prompt Optimization and Learned Ensembling. CoRR Berk Atil, Rebecca J. Passonneau, Ninareh Mehrabi
2025	J	`jnl`	Breaking the Benchmark: Revealing LLM Bias via Minimal Contextual Augmentation. CoRR Kaveh Eskandari Miandoab, Mahammed Kamruzzaman, Arshia Gharooni, Gene Louis Kim, Vasanth Sarathy, Ninareh Mehrabi
2025	J	`jnl`	Co-Evolving Agents: Learning from Failures as Hard Negatives. CoRR Yeonsung Jung, Trilok Padhi, Sina Shaham, Dipika Khullar, Joonhyun Jeong, Ninareh Mehrabi, Eunho Yang
2025	A*	`conf`	DiCoRe: Enhancing Zero-shot Event Detection via Divergent-Convergent LLM Reasoning. EMNLP Tanmay Parekh, Kartik Mehta, Ninareh Mehrabi, Kai-Wei Chang, Nanyun Peng
2025	J	`jnl`	DiCoRe: Enhancing Zero-shot Event Detection via Divergent-Convergent LLM Reasoning. CoRR Tanmay Parekh, Kartik Mehta, Ninareh Mehrabi, Kai-Wei Chang, Nanyun Peng
2025	A*	`conf`	Diagnosing Memorization in Chain-of-Thought Reasoning, One Token at a Time. EMNLP Huihan Li, You Chen, Siyuan Wang, Yixin He, Ninareh Mehrabi, Rahul Gupta, Xiang Ren
2025	J	`jnl`	Diagnosing Memorization in Chain-of-Thought Reasoning, One Token at a Time. CoRR Huihan Li, You Chen, Siyuan Wang, Yixin He, Ninareh Mehrabi, Rahul Gupta, Xiang Ren
2025	J	`jnl`	Evaluating the Critical Risks of Amazon's Nova Premier under the Frontier Model Safety Framework. CoRR Satyapriya Krishna, Ninareh Mehrabi, Abhinav Mohanty, Matteo Memelli, Vincent Ponzo, Payal Motwani, Rahul Gupta
2025	J	`jnl`	K-Edit: Language Model Editing with Contextual Knowledge Awareness. CoRR Elan Markowitz, Anil Ramakrishna, Ninareh Mehrabi, Charith Peris, Rahul Gupta, Kai-Wei Chang, Aram Galstyan
2025	J	`jnl`	Kaleidoscopic Teaming in Multi Agent Simulations. CoRR Ninareh Mehrabi, Tharindu Kumarage, Kai-Wei Chang, Aram Galstyan, Rahul Gupta
2025	—	`conf`	On Localizing and Deleting Toxic Memories in Large Language Models. NAACL (Findings) Anubrata Das, Manoj Kumar, Ninareh Mehrabi, Anil Ramakrishna, Anna Rumshisky, Kai-Wei Chang, Aram Galstyan, Morteza Ziyadi, Rahul Gupta
2025	J	`jnl`	Strategize Globally, Adapt Locally: A Multi-Turn Red Teaming Agent with Dual-Level Learning. CoRR Si Chen, Xiao Yu, Ninareh Mehrabi, Rahul Gupta, Zhou Yu, Ruoxi Jia
2025	—	`conf`	Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation. ACL (Findings) Tharindu Kumarage, Ninareh Mehrabi, Anil Ramakrishna, Xinyan Zhao, Richard S. Zemel, Kai-Wei Chang, Aram Galstyan, Rahul Gupta, Charith Peris
2025	J	`jnl`	Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation. CoRR Tharindu Kumarage, Ninareh Mehrabi, Anil Ramakrishna, Xinyan Zhao, Richard S. Zemel, Kai-Wei Chang, Aram Galstyan, Rahul Gupta, Charith Peris
2024	—	`conf`	Attribute Controlled Fine-tuning for Large Language Models: A Case Study on Detoxification. EMNLP (Findings) Tao Meng, Ninareh Mehrabi, Palash Goyal, Anil Ramakrishna, Aram Galstyan, Richard S. Zemel, Kai-Wei Chang, Rahul Gupta, Charith Peris
2024	J	`jnl`	Attribute Controlled Fine-tuning for Large Language Models: A Case Study on Detoxification. CoRR Tao Meng, Ninareh Mehrabi, Palash Goyal, Anil Ramakrishna, Aram Galstyan, Richard S. Zemel, Kai-Wei Chang, Rahul Gupta, Charith Peris
2024	A*	`conf`	Data Advisor: Dynamic Data Curation for Safety Alignment of Large Language Models. EMNLP Fei Wang, Ninareh Mehrabi, Palash Goyal, Rahul Gupta, Kai-Wei Chang, Aram Galstyan
2024	J	`jnl`	Data Advisor: Dynamic Data Curation for Safety Alignment of Large Language Models. CoRR Fei Wang, Ninareh Mehrabi, Palash Goyal, Rahul Gupta, Kai-Wei Chang, Aram Galstyan
2024	A*	`conf`	FLIRT: Feedback Loop In-context Red Teaming. EMNLP Ninareh Mehrabi, Palash Goyal, Christophe Dupuy, Qian Hu, Shalini Ghosh, Richard S. Zemel, Kai-Wei Chang, Aram Galstyan, Rahul Gupta
2024	—	`conf`	MICo: Preventative Detoxification of Large Language Models through Inhibition Control. NAACL-HLT (Findings) Roy Siegelmann, Ninareh Mehrabi, Palash Goyal, Prasoon Goyal, Lisa Bauer, Jwala Dhamala, Aram Galstyan, Rahul Gupta, Reza Ghanadan
2024	—	`conf`	Prompt Perturbation Consistency Learning for Robust Language Models. EACL (Findings) Yao Qiang, Subhrangshu Nandi, Ninareh Mehrabi, Greg Ver Steeg, Anoop Kumar, Anna Rumshisky, Aram Galstyan
2024	J	`jnl`	Prompt Perturbation Consistency Learning for Robust Language Models. CoRR Yao Qiang, Subhrangshu Nandi, Ninareh Mehrabi, Greg Ver Steeg, Anoop Kumar, Anna Rumshisky, Aram Galstyan
2024	—	`conf`	The steerability of large language models toward data-driven personas. NAACL-HLT Junyi Li, Charith Peris, Ninareh Mehrabi, Palash Goyal, Kai-Wei Chang, Aram Galstyan, Richard S. Zemel, Rahul Gupta
2024	—	`conf`	Tokenization Matters: Navigating Data-Scarce Tokenization for Gender Inclusive Language Technologies. NAACL-HLT (Findings) Anaelia Ovalle, Ninareh Mehrabi, Palash Goyal, Jwala Dhamala, Kai-Wei Chang, Richard S. Zemel, Aram Galstyan, Yuval Pinter, Rahul Gupta
2024	—	`conf`	Tree-of-Traversals: A Zero-Shot Reasoning Algorithm for Augmenting Black-box Language Models with Knowledge Graphs. ACL (1) Elan Markowitz, Anil Ramakrishna, Jwala Dhamala, Ninareh Mehrabi, Charith Peris, Rahul Gupta, Kai-Wei Chang, Aram Galstyan
2024	J	`jnl`	Tree-of-Traversals: A Zero-Shot Reasoning Algorithm for Augmenting Black-box Language Models with Knowledge Graphs. CoRR Elan Markowitz, Anil Ramakrishna, Jwala Dhamala, Ninareh Mehrabi, Charith Peris, Rahul Gupta, Kai-Wei Chang, Aram Galstyan
2023	J	`jnl`	Are you talking to ['xem'] or ['x', 'em']? On Tokenization and Addressing Misgendering in LLMs with Pronoun Tokenization Parity. CoRR Anaelia Ovalle, Ninareh Mehrabi, Palash Goyal, Jwala Dhamala, Kai-Wei Chang, Richard S. Zemel, Aram Galstyan, Rahul Gupta
2023	J	`jnl`	FLIRT: Feedback Loop In-context Red Teaming. CoRR Ninareh Mehrabi, Palash Goyal, Christophe Dupuy, Qian Hu, Shalini Ghosh, Richard S. Zemel, Kai-Wei Chang, Aram Galstyan, Rahul Gupta
2023	J	`jnl`	JAB: Joint Adversarial Prompting and Belief Augmentation. CoRR Ninareh Mehrabi, Palash Goyal, Anil Ramakrishna, Jwala Dhamala, Shalini Ghosh, Richard S. Zemel, Kai-Wei Chang, Aram Galstyan, Rahul Gupta
2023	J	`jnl`	On the steerability of large language models toward data-driven personas. CoRR Junyi Li, Ninareh Mehrabi, Charith Peris, Palash Goyal, Kai-Wei Chang, Aram Galstyan, Richard S. Zemel, Rahul Gupta
2023	—	`conf`	Resolving Ambiguities in Text-to-Image Generative Models. ACL (1) Ninareh Mehrabi, Palash Goyal, Apurv Verma, Jwala Dhamala, Varun Kumar, Qian Hu, Kai-Wei Chang, Richard S. Zemel, Aram Galstyan, Rahul Gupta
2022	J	`jnl`	A Survey on Bias and Fairness in Machine Learning. ACM Comput. Surv. Ninareh Mehrabi, Fred Morstatter, Nripsuta Saxena, Kristina Lerman, Aram Galstyan
2022	J	`jnl`	Is the Elephant Flying? Resolving Ambiguities in Text-to-Image Generative Models. CoRR Ninareh Mehrabi, Palash Goyal, Apurv Verma, Jwala Dhamala, Varun Kumar, Qian Hu, Kai-Wei Chang, Richard S. Zemel, Aram Galstyan, Rahul Gupta
2022	—	`conf`	Robust Conversational Agents against Imperceptible Toxicity Triggers. NAACL-HLT Ninareh Mehrabi, Ahmad Beirami, Fred Morstatter, Aram Galstyan
2022	J	`jnl`	Robust Conversational Agents against Imperceptible Toxicity Triggers. CoRR Ninareh Mehrabi, Ahmad Beirami, Fred Morstatter, Aram Galstyan
2022	J	`jnl`	Towards Multi-Objective Statistically Fair Federated Learning. CoRR Ninareh Mehrabi, Cyprien de Lichy, John McKay, Cynthia He, William Campbell
2022	J	`jnl`	Where Does Bias in Common Sense Knowledge Models Come From? IEEE Internet Comput. Sara Melotte, Filip Ilievski, Linglan Zhang, Aditya Malte, Namita Mutha, Fred Morstatter, Ninareh Mehrabi
2021	J	`jnl`	Attributing Fair Decisions with Attention Interventions. CoRR Ninareh Mehrabi, Umang Gupta, Fred Morstatter, Greg Ver Steeg, Aram Galstyan
2021	A*	`conf`	Exacerbating Algorithmic Bias through Fairness Attacks. AAAI Ninareh Mehrabi, Muhammad Naveed, Fred Morstatter, Aram Galstyan
2021	—	`conf`	Lawyers are Dishonest? Quantifying Representational Harms in Commonsense Knowledge Resources. EMNLP (1) Ninareh Mehrabi, Pei Zhou, Fred Morstatter, Jay Pujara, Xiang Ren, Aram Galstyan
2021	J	`jnl`	Lawyers are Dishonest? Quantifying Representational Harms in Commonsense Knowledge Resources. CoRR Ninareh Mehrabi, Pei Zhou, Fred Morstatter, Jay Pujara, Xiang Ren, Aram Galstyan
2020	J	`jnl`	Exacerbating Algorithmic Bias through Fairness Attacks. CoRR Ninareh Mehrabi, Muhammad Naveed, Fred Morstatter, Aram Galstyan
2020	—	`conf`	Man is to Person as Woman is to Location: Measuring Gender Bias in Named Entity Recognition. HT Ninareh Mehrabi, Thamme Gowda, Fred Morstatter, Nanyun Peng, Aram Galstyan
2020	J	`jnl`	Statistical Equity: A Fairness Classification Objective. CoRR Ninareh Mehrabi, Yuzhong Huang, Fred Morstatter
2020	J	`jnl`	The Leaky Pipeline in Physics Publishing. CoRR Clara O. Ross, Aditya Gupta, Ninareh Mehrabi, Goran Muric, Kristina Lerman
2019	J	`jnl`	A Survey on Bias and Fairness in Machine Learning. CoRR Ninareh Mehrabi, Fred Morstatter, Nripsuta Saxena, Kristina Lerman, Aram Galstyan
2019	J	`jnl`	Debiasing Community Detection: The Importance of Lowly-Connected Nodes. CoRR Ninareh Mehrabi, Fred Morstatter, Nanyun Peng, Aram Galstyan
2019	B	`conf`	Debiasing community detection: the importance of lowly connected nodes. ASONAM Ninareh Mehrabi, Fred Morstatter, Nanyun Peng, Aram Galstyan
2019	J	`jnl`	Man is to Person as Woman is to Location: Measuring Gender Bias in Named Entity Recognition. CoRR Ninareh Mehrabi, Thamme Gowda, Fred Morstatter, Nanyun Peng, Aram Galstyan
2018	J	`jnl`	DynamicGEM: A Library for Dynamic Graph Embedding Methods. CoRR Palash Goyal, Sujit Rokka Chhetri, Ninareh Mehrabi, Emilio Ferrara, Arquimedes Canedo