Alert button
Picture for Ninareh Mehrabi

Ninareh Mehrabi

Alert button

Prompt Perturbation Consistency Learning for Robust Language Models

Feb 24, 2024
Yao Qiang, Subhrangshu Nandi, Ninareh Mehrabi, Greg Ver Steeg, Anoop Kumar, Anna Rumshisky, Aram Galstyan

Viaarxiv icon

Are you talking to ['xem'] or ['x', 'em']? On Tokenization and Addressing Misgendering in LLMs with Pronoun Tokenization Parity

Dec 21, 2023
Anaelia Ovalle, Ninareh Mehrabi, Palash Goyal, Jwala Dhamala, Kai-Wei Chang, Richard Zemel, Aram Galstyan, Rahul Gupta

Viaarxiv icon

JAB: Joint Adversarial Prompting and Belief Augmentation

Nov 16, 2023
Ninareh Mehrabi, Palash Goyal, Anil Ramakrishna, Jwala Dhamala, Shalini Ghosh, Richard Zemel, Kai-Wei Chang, Aram Galstyan, Rahul Gupta

Viaarxiv icon

On the steerability of large language models toward data-driven personas

Nov 08, 2023
Junyi Li, Ninareh Mehrabi, Charith Peris, Palash Goyal, Kai-Wei Chang, Aram Galstyan, Richard Zemel, Rahul Gupta

Viaarxiv icon

FLIRT: Feedback Loop In-context Red Teaming

Aug 08, 2023
Ninareh Mehrabi, Palash Goyal, Christophe Dupuy, Qian Hu, Shalini Ghosh, Richard Zemel, Kai-Wei Chang, Aram Galstyan, Rahul Gupta

Figure 1 for FLIRT: Feedback Loop In-context Red Teaming
Figure 2 for FLIRT: Feedback Loop In-context Red Teaming
Figure 3 for FLIRT: Feedback Loop In-context Red Teaming
Figure 4 for FLIRT: Feedback Loop In-context Red Teaming
Viaarxiv icon

Is the Elephant Flying? Resolving Ambiguities in Text-to-Image Generative Models

Nov 17, 2022
Ninareh Mehrabi, Palash Goyal, Apurv Verma, Jwala Dhamala, Varun Kumar, Qian Hu, Kai-Wei Chang, Richard Zemel, Aram Galstyan, Rahul Gupta

Figure 1 for Is the Elephant Flying? Resolving Ambiguities in Text-to-Image Generative Models
Figure 2 for Is the Elephant Flying? Resolving Ambiguities in Text-to-Image Generative Models
Figure 3 for Is the Elephant Flying? Resolving Ambiguities in Text-to-Image Generative Models
Figure 4 for Is the Elephant Flying? Resolving Ambiguities in Text-to-Image Generative Models
Viaarxiv icon

Robust Conversational Agents against Imperceptible Toxicity Triggers

May 05, 2022
Ninareh Mehrabi, Ahmad Beirami, Fred Morstatter, Aram Galstyan

Figure 1 for Robust Conversational Agents against Imperceptible Toxicity Triggers
Figure 2 for Robust Conversational Agents against Imperceptible Toxicity Triggers
Figure 3 for Robust Conversational Agents against Imperceptible Toxicity Triggers
Figure 4 for Robust Conversational Agents against Imperceptible Toxicity Triggers
Viaarxiv icon

Towards Multi-Objective Statistically Fair Federated Learning

Jan 24, 2022
Ninareh Mehrabi, Cyprien de Lichy, John McKay, Cynthia He, William Campbell

Figure 1 for Towards Multi-Objective Statistically Fair Federated Learning
Figure 2 for Towards Multi-Objective Statistically Fair Federated Learning
Figure 3 for Towards Multi-Objective Statistically Fair Federated Learning
Figure 4 for Towards Multi-Objective Statistically Fair Federated Learning
Viaarxiv icon

Attributing Fair Decisions with Attention Interventions

Sep 08, 2021
Ninareh Mehrabi, Umang Gupta, Fred Morstatter, Greg Ver Steeg, Aram Galstyan

Figure 1 for Attributing Fair Decisions with Attention Interventions
Figure 2 for Attributing Fair Decisions with Attention Interventions
Figure 3 for Attributing Fair Decisions with Attention Interventions
Figure 4 for Attributing Fair Decisions with Attention Interventions
Viaarxiv icon

Lawyers are Dishonest? Quantifying Representational Harms in Commonsense Knowledge Resources

Mar 21, 2021
Ninareh Mehrabi, Pei Zhou, Fred Morstatter, Jay Pujara, Xiang Ren, Aram Galstyan

Figure 1 for Lawyers are Dishonest? Quantifying Representational Harms in Commonsense Knowledge Resources
Figure 2 for Lawyers are Dishonest? Quantifying Representational Harms in Commonsense Knowledge Resources
Figure 3 for Lawyers are Dishonest? Quantifying Representational Harms in Commonsense Knowledge Resources
Figure 4 for Lawyers are Dishonest? Quantifying Representational Harms in Commonsense Knowledge Resources
Viaarxiv icon