430 citations · 898 across the 25 of their papers we have counts for
25 papers
The Activist's Guide to the Decentralized Social Universe: A Framework for Exploring How Decentralized Social Networks Can Support Collective Action
Sybille Légitime, Harini Suresh
The overreaches of mainstream social media platforms have been extensively reported and studied. For activist communities, these platforms pose risks of surveillance, censorship, o…
Which Institutional Frameworks Do Chatbots Assume? Auditing Jurisdictional Defaults in Multilingual LLMs
Zhizhi Wang, Harini Suresh
LLMs increasingly answer questions about taxes, labor protections, healthcare, education, pensions, and administrative procedures, where usefulness often depends on the applicable…
Representational Harms in LLM-Generated Narratives Against Global Majority Nationalities
Ilana Nguyen, Harini Suresh, Thema Monroe-White +1
Large language models (LLMs) are increasingly used for text generation tasks from everyday use to high-stakes enterprise and government applications, including simulated interviews…
Reimagining Data Work: Participatory Annotation Workshops as Feminist Practice
Yujia Gao, Isadora Araujo Cruxên, Helena Suárez Val +3
AI systems depend on the invisible and undervalued labor of data workers, who are often treated as interchangeable units rather than collaborators with meaningful expertise. Critic…
How to Stop Playing Whack-a-Mole: Mapping the Ecosystem of Technologies Facilitating AI-Generated Non-Consensual Intimate Images
Michelle L. Ding, Harini Suresh, Suresh Venkatasubramanian
The last decade has witnessed a rapid advancement of generative AI technology that significantly scaled the accessibility of AI-generated non-consensual intimate images (AIG-NCII),…
Audit Trails for Accountability in Large Language Models
Victor Ojewale, Harini Suresh, Suresh Venkatasubramanian
Large language models (LLMs) are increasingly embedded in consequential decisions across healthcare, finance, employment, and public services. Yet accountability remains fragile be…
The Malicious Technical Ecosystem: Exposing Limitations in Technical Governance of AI-Generated Non-Consensual Intimate Images of Adults
Michelle L. Ding, Harini Suresh
In this paper, we adopt a survivor-centered approach to locate and dissect the role of sociotechnical AI governance in preventing AI-Generated Non-Consensual Intimate Images (AIG-N…
"Ownership, Not Just Happy Talk": Co-Designing a Participatory Large Language Model for Journalism
Emily Tseng, Meg Young, Marianne Aubin Le Quéré +2
Journalism has emerged as an essential domain for understanding the uses, limitations, and impacts of large language models (LLMs) in the workplace. News organizations face diverge…
Participation in the age of foundation models
Harini Suresh, Emily Tseng, Meg Young +3
Growing interest and investment in the capabilities of foundation models has positioned such systems to impact a wide array of public services. Alongside these opportunities is the…
Using large language models to promote health equity
Emma Pierson, Divya Shanmugam, Rajiv Movva +12
Advances in large language models (LLMs) have driven an explosion of interest about their societal impacts. Much of the discourse around how they will impact social equity has been…
Improved Text Classification via Test-Time Augmentation
Helen Lu, Divya Shanmugam, Harini Suresh +1
Test-time augmentation -- the aggregation of predictions across transformed examples of test inputs -- is an established technique to improve the performance of image classificatio…
Saliency Cards: A Framework to Characterize and Compare Saliency Methods
Angie Boggust, Harini Suresh, Hendrik Strobelt +2
Saliency methods are a common class of machine learning interpretability techniques that calculate how important each input feature is to a model's output. We find that, with the r…
Intuitively Assessing ML Model Reliability through Example-Based Explanations and Editing Model Inputs
Harini Suresh, Kathleen M. Lewis, John V. Guttag +1
Interpretability methods aim to help users build trust in and understand the capabilities of machine learning models. However, existing approaches often rely on abstract, complex v…
Beyond Expertise and Roles: A Framework to Characterize the Stakeholders of Interpretable Machine Learning and their Needs
Harini Suresh, Steven R. Gomez, Kevin K. Nam +1
To ensure accountability and mitigate harm, it is critical that diverse stakeholders can interrogate black-box automated systems and find information that is understandable, releva…
Underspecification Presents Challenges for Credibility in Modern Machine Learning
Alexander D'Amour, Katherine Heller, Dan Moldovan +37
ML models often exhibit unexpectedly poor behavior when they are deployed in real-world domains. We identify underspecification as a key reason for these failures. An ML pipeline i…
Misplaced Trust: Measuring the Interference of Machine Learning in Human Decision-Making
Harini Suresh, Natalie Lao, Ilaria Liccardi
ML decision-aid systems are increasingly common on the web, but their successful integration relies on people trusting them appropriately: they should use the system to fill in gap…
Image segmentation of liver stage malaria infection with spatial uncertainty sampling
Ava P. Soleimany, Harini Suresh, Jose Javier Gonzalez Ortiz +4
Global eradication of malaria depends on the development of drugs effective against the silent, yet obligate liver stage of the disease. The gold standard in drug development remai…
A Framework for Understanding Sources of Harm throughout the Machine Learning Life Cycle
Harini Suresh, John V. Guttag
As machine learning (ML) increasingly affects people and society, awareness of its potential unwanted consequences has also grown. To anticipate, prevent, and mitigate undesirable…
Racial Disparities and Mistrust in End-of-Life Care
Willie Boag, Harini Suresh, Leo Anthony Celi +2
There are established racial disparities in healthcare, including during end-of-life care, when poor communication and trust can lead to suboptimal outcomes for patients and their…
Modeling Mistrust in End-of-Life Care
Willie Boag, Harini Suresh, Leo Anthony Celi +2
In this work, we characterize the doctor-patient relationship using a machine learning-derived trust score. We show that this score has statistically significant racial association…
Learning Tasks for Multitask Learning: Heterogenous Patient Populations in the ICU
Harini Suresh, Jen J. Gong, John Guttag
Machine learning approaches have been effective in predicting adverse outcomes in different clinical settings. These models are often developed and evaluated on datasets with heter…
Clinical Intervention Prediction and Understanding using Deep Networks
Harini Suresh, Nathan Hunt, Alistair Johnson +3
Real-time prediction of clinical interventions remains a challenge within intensive care units (ICUs). This task is complicated by data sources that are noisy, sparse, heterogeneou…
The Use of Autoencoders for Discovering Patient Phenotypes
Harini Suresh, Peter Szolovits, Marzyeh Ghassemi
We use autoencoders to create low-dimensional embeddings of underlying patient phenotypes that we hypothesize are a governing factor in determining how different patients will reac…
Feature Representation for ICU Mortality
Harini Suresh
Good predictors of ICU Mortality have the potential to identify high-risk patients earlier, improve ICU resource allocation, or create more accurate population-level risk models. M…