no code implementations • 24 Feb 2024 • Yao Qiang, Subhrangshu Nandi, Ninareh Mehrabi, Greg Ver Steeg, Anoop Kumar, Anna Rumshisky, Aram Galstyan
However, their performance on sequence labeling tasks such as intent classification and slot filling (IC-SF), which is a central component in personal assistant systems, lags significantly behind discriminative models.
no code implementations • 19 Dec 2023 • Anaelia Ovalle, Ninareh Mehrabi, Palash Goyal, Jwala Dhamala, Kai-Wei Chang, Richard Zemel, Aram Galstyan, Yuval Pinter, Rahul Gupta
Our paper is the first to link LLM misgendering to tokenization and deficient neopronoun grammar, indicating that LLMs unable to correctly treat neopronouns as pronouns are more prone to misgender.
no code implementations • 16 Nov 2023 • Ninareh Mehrabi, Palash Goyal, Anil Ramakrishna, Jwala Dhamala, Shalini Ghosh, Richard Zemel, Kai-Wei Chang, Aram Galstyan, Rahul Gupta
With the recent surge of language models in different applications, attention to safety and robustness of these models has gained significant importance.
no code implementations • 8 Nov 2023 • Junyi Li, Ninareh Mehrabi, Charith Peris, Palash Goyal, Kai-Wei Chang, Aram Galstyan, Richard Zemel, Rahul Gupta
Large language models (LLMs) are known to generate biased responses where the opinions of certain groups and populations are underrepresented.
no code implementations • 8 Aug 2023 • Ninareh Mehrabi, Palash Goyal, Christophe Dupuy, Qian Hu, Shalini Ghosh, Richard Zemel, Kai-Wei Chang, Aram Galstyan, Rahul Gupta
Here we propose an automatic red teaming framework that evaluates a given model and exposes its vulnerabilities against unsafe and inappropriate content generation.
no code implementations • 17 Nov 2022 • Ninareh Mehrabi, Palash Goyal, Apurv Verma, Jwala Dhamala, Varun Kumar, Qian Hu, Kai-Wei Chang, Richard Zemel, Aram Galstyan, Rahul Gupta
Natural language often contains ambiguities that can lead to misinterpretation and miscommunication.
1 code implementation • NAACL 2022 • Ninareh Mehrabi, Ahmad Beirami, Fred Morstatter, Aram Galstyan
Existing work to generate such attacks is either based on human-generated attacks which is costly and not scalable or, in case of automatic attacks, the attack vector does not conform to human-like language, which can be detected using a language model loss.
no code implementations • 24 Jan 2022 • Ninareh Mehrabi, Cyprien de Lichy, John McKay, Cynthia He, William Campbell
With this goal in mind, we conduct studies to show that FL is able to satisfy different fairness metrics under different data regimes consisting of different types of clients.
1 code implementation • NAACL (TrustNLP) 2022 • Ninareh Mehrabi, Umang Gupta, Fred Morstatter, Greg Ver Steeg, Aram Galstyan
The widespread use of Artificial Intelligence (AI) in consequential domains, such as healthcare and parole decision-making systems, has drawn intense scrutiny on the fairness of these methods.
no code implementations • EMNLP 2021 • Ninareh Mehrabi, Pei Zhou, Fred Morstatter, Jay Pujara, Xiang Ren, Aram Galstyan
In addition, we analyze two downstream models that use ConceptNet as a source for commonsense knowledge and find the existence of biases in those models as well.
1 code implementation • 16 Dec 2020 • Ninareh Mehrabi, Muhammad Naveed, Fred Morstatter, Aram Galstyan
Algorithmic fairness has attracted significant attention in recent years, with many quantitative measures suggested for characterizing the fairness of different machine learning algorithms.
1 code implementation • 14 May 2020 • Ninareh Mehrabi, Yuzhong Huang, Fred Morstatter
We formalize our definition of fairness, and motivate it with its appropriate contexts.
1 code implementation • 24 Oct 2019 • Ninareh Mehrabi, Thamme Gowda, Fred Morstatter, Nanyun Peng, Aram Galstyan
We study the bias in several state-of-the-art named entity recognition (NER) models---specifically, a difference in the ability to recognize male and female names as PERSON entity types.
2 code implementations • 23 Aug 2019 • Ninareh Mehrabi, Fred Morstatter, Nripsuta Saxena, Kristina Lerman, Aram Galstyan
With the commercialization of these systems, researchers are becoming aware of the biases that these applications can contain and have attempted to address them.
1 code implementation • 26 Nov 2018 • Palash Goyal, Sujit Rokka Chhetri, Ninareh Mehrabi, Emilio Ferrara, Arquimedes Canedo
DynamicGEM is an open-source Python library for learning node representations of dynamic graphs.