Portrait of Golnoosh Farnadi

Golnoosh Farnadi

Core Academic Member
farnadig@mila.quebec
Canada CIFAR AI Chair
Assistant Professor, McGill University, School of Computer Science
Adjunct Professor, Université de Montréal, Department of Computer Science and Operations Research
Visiting Faculty Researcher, Google
Research Topics
Deep Learning
Generative Models
Website
Google Scholar
LinkedIn
X

Biography

Golnoosh Farnadi is an assistant professor at the School of Computer Science, McGill University, and an adjunct professor at Université de Montréal. She is a core academic member of Mila – Quebec Artificial Intelligence Institute and holds a Canada CIFAR AI Chair.

Farnadi founded and is a principal investigator of the EQUAL lab at Mila / McGill University. The EQUAL lab (EQuity & EQuality Using AI and Learning algorithms) is a cutting-edge research laboratory dedicated to advancing the fields of algorithmic fairness and responsible AI.

Current Students

Mina Arzaghi
PhD - HEC Montréal
Website
Github
Florian Carichon
Postdoctorate - McGill University
Khaoula Chehbouni
PhD - McGill University
Co-supervisor :
Jackie Cheung
kchehbouni@gmail.com
Website
Github
Google Scholar
Chataigner Cléa
Research Intern - McGill University
Alireza Farashah
Master's Research - McGill University
Co-supervisor :
Negar Rostamzadeh
Website
Github
Marylou Fauchard
Master's Research - Université de Montréal
Principal supervisor :
Margarida Carvalho
marylou.fauchard@mila.quebec
Prakhar Ganesh
PhD - McGill University
prakhar.ganesh@mila.quebec
Website
Github
Google Scholar
Aditi Khandelwal
PhD - McGill University
Co-supervisor :
Siva Reddy
Github
Google Scholar
Saber Malekmohammadi
Research Intern - McGill University
saber.malekmohammadi@mila.quebec
Armin Moradi
Master's Research - Université de Montréal
arminmoradi785@gmail.com
Website
Github
Google Scholar
Yash Raj More
Master's Research - Université de Montréal
Elaheh Rahmati
Master's Research - Polytechnique Montréal
William St-Arnaud
PhD - Université de Montréal
Co-supervisor :
Margarida Carvalho
Rohan Sukumaran
Master's Research - Université de Montréal
Website
Github
Google Scholar
Afaf Taïk
Postdoctorate - Université de Montréal
Jesse Thibodeau
Independent visiting researcher - HEC Montréal
Github

Publications

On the Role of Prompt Multiplicity in LLM Hallucination Evaluation
Prakhar Ganesh
Reza Shokri
Golnoosh Farnadi
Large language models (LLMs) are known to "hallucinate" by generating false or misleading outputs. Existing hallucination benchmarks often o… (see more)verlook prompt sensitivity, due to stable accuracy scores despite prompt variations. However, such stability can be misleading. In this work, we introduce prompt multiplicity--the multiplicity of individual hallucinations depending on the input prompt--and study its role in LLM hallucination benchmarks. We find severe multiplicity, with even more than 50% of responses changing between correct and incorrect answers simply based on the prompt for certain benchmarks, like Med-HALT. Prompt multiplicity also gives us the lens to distinguish between randomness in generation and consistent factual inaccuracies, providing a more nuanced understanding of LLM hallucinations and their real-world harms. By situating our discussion within existing hallucination taxonomies--supporting their quantification--and exploring its relationship with uncertainty in generation, we highlight how prompt multiplicity fills a critical gap in the literature on LLM hallucinations.
2025-03-05
ICLR.cc/2025/Workshop/BuildingTrust (accepted)
openreview.net
openreview.net
UNLEARNING GEO-CULTURAL STEREOTYPES IN MULTILINGUAL LLMS
Alireza Dehghanpour Farashah
Aditi Khandelwal
Negar Rostamzadeh
Golnoosh Farnadi
As multilingual generative models become more widely used, most safety and fairness evaluation techniques still focus on English-language re… (see more)sources, while overlooking important cross-cultural factors. This limitation raises concerns about fairness and safety, particularly regarding geoculturally situated stereotypes that hinder the models’ global inclusivity. In this work, we present preliminary findings on the impact of stereotype unlearning across languages, specifically in English, French, and Hindi. Using an adapted version of the SeeGULL dataset, we analyze how unlearning stereotypes in one language influences other languages within multilingual large language models. Our study evaluates two model families, Llama-3.1-8B and Aya-Expanse-8B, to assess whether unlearning in one linguistic context transfers across languages, potentially mitigating or exacerbating biases in multilingual settings.
2025-03-05
ICLR.cc/2025/Workshop/BuildingTrust (accepted)
openreview.net
openreview.net
Bridging Causality, Individual Fairness, and Adversarial Robustness in the Absence of Structural Causal Model
Ahmad Reza Ehyaei
Golnoosh Farnadi
Samira Samadi
Despite the essential need for comprehensive considerations in responsible AI, factors such as robustness, fairness, and causality are often… (see more) studied in isolation. Adversarial perturbation, used to identify vulnerabilities in models, and individual fairness, aiming for equitable treatment of similar individuals, despite initial differences, both depend on metrics to generate comparable input data instances. Previous attempts to define such joint metrics often lack general assumptions about data and were unable to reflect counterfactual proximity. To address this, our paper introduces a \emph{causal fair metric} formulated based on causal structures encompassing sensitive attributes and protected causal perturbation. To enhance the practicality of our metric, we propose metric learning as a method for metric estimation and deployment in real-world problems in the absence of structural causal models. We also demonstrate the applications of the causal fair metric in classifiers. Empirical evaluation of real-world and synthetic datasets illustrates the effectiveness of our proposed metric in achieving an accurate classifier with fairness, resilience to adversarial perturbations, and a nuanced understanding of causal relationships.
2025-02-03
TMLR (accepted)
openreview.net
openreview.net
What Secrets Do Your Manifolds Hold? Understanding the Local Geometry of Generative Models
Ahmed Imtiaz Humayun
Ibtihel Amara
Cristina Nader Vasconcelos
Deepak Ramachandran
Candice Schumann
Junfeng He
Katherine A Heller
Golnoosh Farnadi
Negar Rostamzadeh
Mohammad Havaei
Deep Generative Models are frequently used to learn continuous representations of complex data distributions using a finite number of sample… (see more)s. For any generative model, including pre-trained foundation models with GAN, Transformer or Diffusion architectures, generation performance can vary significantly based on which part of the learned data manifold is sampled. In this paper we study the post-training local geometry of the learned manifold and its relationship to generation outcomes for models ranging from toy settings to the latent decoder of the near state-of-the-art Stable Diffusion 1.4 Text-to-Image model. Building on the theory of continuous piecewise-linear (CPWL) generators, we characterize the local geometry in terms of three geometric descriptors - scaling (
2025-01-22
ICLR.cc/2025/Conference (poster)
openreview.net
openreview.net
What Secrets Do Your Manifolds Hold? Understanding the Local Geometry of Generative Models
Ahmed Imtiaz Humayun
Ibtihel Amara
Cristina Nader Vasconcelos
Candice Schumann
Golnoosh Farnadi
Deepak Ramachandran
Negar Rostamzadeh
Junfeng He
Mohammad Havaei
Katherine A Heller
2025-01-22
ICLR.cc/2025/Conference (poster)
openreview.net
openreview.net
Embedding Cultural Diversity in Prototype-based Recommender Systems
Armin Moradi
Nicola Neophytou
Florian Carichon
Golnoosh Farnadi
Popularity bias in recommender systems can increase cultural overrepresentation by favoring norms from dominant cultures and marginalizing u… (see more)nderrepresented groups. This issue is critical for platforms offering cultural products, as they influence consumption patterns and human perceptions. In this work, we address popularity bias by identifying demographic biases within prototype-based matrix factorization methods. Using the country of origin as a proxy for cultural identity, we link this demographic attribute to popularity bias by refining the embedding space learning process. First, we propose filtering out irrelevant prototypes to improve representativity. Second, we introduce a regularization technique to enforce a uniform distribution of prototypes within the embedding space. Across four datasets, our results demonstrate a 27\% reduction in the average rank of long-tail items and a 2\% reduction in the average rank of items from underrepresented countries. Additionally, our model achieves a 2\% improvement in HitRatio@10 compared to the state-of-the-art, highlighting that fairness is enhanced without compromising recommendation quality. Moreover, the distribution of prototypes leads to more inclusive explanations by better aligning items with diverse prototypes.
2024-12-18
ArXiv (preprint)
doi.org
arxiv.org
Embedding Cultural Diversity in Prototype-based Recommender Systems
Armin Moradi
Nicola Neophytou
Florian Carichon
Golnoosh Farnadi
Popularity bias in recommender systems can increase cultural overrepresentation by favoring norms from dominant cultures and marginalizing u… (see more)nderrepresented groups. This issue is critical for platforms offering cultural products, as they influence consumption patterns and human perceptions. In this work, we address popularity bias by identifying demographic biases within prototype-based matrix factorization methods. Using the country of origin as a proxy for cultural identity, we link this demographic attribute to popularity bias by refining the embedding space learning process. First, we propose filtering out irrelevant prototypes to improve representativity. Second, we introduce a regularization technique to enforce a uniform distribution of prototypes within the embedding space. Across four datasets, our results demonstrate a 27\% reduction in the average rank of long-tail items and a 2\% reduction in the average rank of items from underrepresented countries. Additionally, our model achieves a 2\% improvement in HitRatio@10 compared to the state-of-the-art, highlighting that fairness is enhanced without compromising recommendation quality. Moreover, the distribution of prototypes leads to more inclusive explanations by better aligning items with diverse prototypes.
2024-12-18
ArXiv (preprint)
doi.org
arxiv.org
Embedding Cultural Diversity in Prototype-based Recommender Systems
Armin Moradi
Nicola Neophytou
Florian Carichon
Golnoosh Farnadi
Popularity bias in recommender systems can increase cultural overrepresentation by favoring norms from dominant cultures and marginalizing u… (see more)nderrepresented groups. This issue is critical for platforms offering cultural products, as they influence consumption patterns and human perceptions. In this work, we address popularity bias by identifying demographic biases within prototype-based matrix factorization methods. Using the country of origin as a proxy for cultural identity, we link this demographic attribute to popularity bias by refining the embedding space learning process. First, we propose filtering out irrelevant prototypes to improve representativity. Second, we introduce a regularization technique to enforce a uniform distribution of prototypes within the embedding space. Across four datasets, our results demonstrate a 27\% reduction in the average rank of long-tail items and a 2\% reduction in the average rank of items from underrepresented countries. Additionally, our model achieves a 2\% improvement in HitRatio@10 compared to the state-of-the-art, highlighting that fairness is enhanced without compromising recommendation quality. Moreover, the distribution of prototypes leads to more inclusive explanations by better aligning items with diverse prototypes.
2024-12-18
ArXiv (preprint)
arxiv.org
arxiv.org
Different Horses for Different Courses: Comparing Bias Mitigation Algorithms in ML
Prakhar Ganeesh
Usman Gohar
Lu Cheng
Golnoosh Farnadi
With fairness concerns gaining significant attention in Machine Learning (ML), several bias mitigation techniques have been proposed, often … (see more)compared against each other to find the best method. These benchmarking efforts tend to use a common setup for evaluation under the assumption that providing a uniform environment ensures a fair comparison. However, bias mitigation techniques are sensitive to hyperparameter choices, random seeds, feature selection, etc., meaning that comparison on just one setting can unfairly favour certain algorithms. In this work, we show significant variance in fairness achieved by several algorithms and the influence of the learning pipeline on fairness scores. We highlight that most bias mitigation techniques can achieve comparable performance, given the freedom to perform hyperparameter optimization, suggesting that the choice of the evaluation parameters-rather than the mitigation technique itself-can sometimes create the perceived superiority of one method over another. We hope our work encourages future research on how various choices in the lifecycle of developing an algorithm impact fairness, and trends that guide the selection of appropriate algorithms.
2024-11-17
ArXiv (preprint)
arxiv.org
arxiv.org
Different Horses for Different Courses: Comparing Bias Mitigation Algorithms in ML
Prakhar Ganeesh
Usman Gohar
Lu Cheng
Golnoosh Farnadi
With fairness concerns gaining significant attention in Machine Learning (ML), several bias mitigation techniques have been proposed, often … (see more)compared against each other to find the best method. These benchmarking efforts tend to use a common setup for evaluation under the assumption that providing a uniform environment ensures a fair comparison. However, bias mitigation techniques are sensitive to hyperparameter choices, random seeds, feature selection, etc., meaning that comparison on just one setting can unfairly favour certain algorithms. In this work, we show significant variance in fairness achieved by several algorithms and the influence of the learning pipeline on fairness scores. We highlight that most bias mitigation techniques can achieve comparable performance, given the freedom to perform hyperparameter optimization, suggesting that the choice of the evaluation parameters-rather than the mitigation technique itself-can sometimes create the perceived superiority of one method over another. We hope our work encourages future research on how various choices in the lifecycle of developing an algorithm impact fairness, and trends that guide the selection of appropriate algorithms.
2024-11-17
ArXiv (preprint)
doi.org
arxiv.org
Beyond the Safety Bundle: Auditing the Helpful and Harmless Dataset
Khaoula Chehbouni
Jonathan Colacco-Carr
Yash More
Jackie Ck Cheung
Golnoosh Farnadi
In an effort to mitigate the harms of large language models (LLMs), learning from human feedback (LHF) has been used to steer LLMs towards o… (see more)utputs that are intended to be both less harmful and more helpful. Despite the widespread adoption of LHF in practice, the quality of this feedback and its effectiveness as a safety mitigation technique remain unclear. This study addresses these issues by auditing the widely-used Helpful and Harmless (HH) dataset by Anthropic. Our work includes: (1) a thorough investigation of the dataset's content through both manual and automated evaluation; (2) experiments demonstrating the dataset's impact on models' safety; and (3) an analysis of the 100 most influential papers citing this dataset. Through our audit, we showcase how conceptualization failures and quality issues identified in the HH dataset can create additional harms by leading to disparate safety behaviors across demographic groups. Our findings highlight the need for more nuanced, context-sensitive approaches to safety mitigation in LLMs.
2024-11-12
ArXiv (preprint)
doi.org
arxiv.org
Beyond the Safety Bundle: Auditing the Helpful and Harmless Dataset
Khaoula Chehbouni
Jonathan Colaco Carr
Yash More
Jackie Cheung
Golnoosh Farnadi
In an effort to mitigate the harms of large language models (LLMs), learning from human feedback (LHF) has been used to steer LLMs towards o… (see more)utputs that are intended to be both less harmful and more helpful. Despite the widespread adoption of LHF in practice, the quality of this feedback and its effectiveness as a safety mitigation technique remain unclear. This study addresses these issues by auditing the widely-used Helpful and Harmless (HH) dataset by Anthropic. Our work includes: (1) a thorough investigation of the dataset's content through both manual and automated evaluation; (2) experiments demonstrating the dataset's impact on models' safety; and (3) an analysis of the 100 most influential papers citing this dataset. Through our audit, we showcase how conceptualization failures and quality issues identified in the HH dataset can create additional harms by leading to disparate safety behaviors across demographic groups. Our findings highlight the need for more nuanced, context-sensitive approaches to safety mitigation in LLMs.
2024-11-12
ArXiv (preprint)
doi.org
arxiv.org