AI & Society Lab Prof. Sorelle Friedler, Haverford College

Research

The AI & Society Lab conducts research about the societal impacts of AI and how various AI governance procedures and technical mechanisms can help to bring about better societal outcomes. This includes work along a variety of ongoing and overlapping societal themes. Work by the lab also includes developing interpretability techniques and using them to further science.

AI and Democracy AI and Speech AI and Civil Rights Fairness and Machine Learning AI Auditing AI Governance Interpretable Machine Learning AI and the Environment AI for Science

Highlighted

Auditing GPT s Content Moderation Guardrails: Can ChatGPT Write Your Favorite TV Show

Auditing GPT's Content Moderation Guardrails: Can ChatGPT Write Your Favorite TV Show?

Yaaseen Mahomed, Charlie M. Crawford, Sanjana Gautam, Sorelle A. Friedler, Danaé Metaxa

The 2024 ACM Conference on Fairness Accountability and Transparency · 2024

AI Auditing AI and Speech

The Im possibility of fairness

The (Im)possibility of fairness

Sorelle A. Friedler, Carlos Scheidegger, Suresh Venkatasubramanian

Communications of the ACM · 2021

Fairness and Machine Learning

Fairness and Abstraction in Sociotechnical Systems

Fairness and Abstraction in Sociotechnical Systems

Andrew D. Selbst, danah boyd, Sorelle A. Friedler, Suresh Venkatasubramanian, Janet Vertesi

Proceedings of the Conference on Fairness, Accountability, and Transparency · 2019

Fairness and Machine Learning AI and Civil Rights

Machine-learning-assisted materials discovery using failed experiments

Machine-learning-assisted materials discovery using failed experiments

Paul Raccuglia, Katherine C. Elbert, Philip D. F. Adler, Casey Falk, Malia B. Wenny, Aurelio Mollo, Matthias Zeller, Sorelle A. Friedler, Joshua Schrier, Alexander J. Norquist

Nature · 2016

AI for Science Interpretable Machine Learning

Certifying and Removing Disparate Impact

Certifying and Removing Disparate Impact

Michael Feldman, Sorelle A. Friedler, John Moeller, Carlos Scheidegger, Suresh Venkatasubramanian

Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · 2015

Fairness and Machine Learning AI and Civil Rights

Selected in-progress works

AI Watchman

AI Watchman

Yunlang Dai, Emma Lurie, Danaé Metaxa, Sorelle A. Friedler

Chatbots rely on content moderation to keep undesireable content, like violent or sexual content, from being generated. But such filters can also block the generation of other information. In this project, we longitudinally track what societal topics are refused by OpenAI’s GPT series and DeepSeek’s chatbot.

All

2026

Triangulating Across U.S. Federal AI Transparency Regimes

Triangulating Across U.S. Federal AI Transparency Regimes

Emma Lurie, Emma Fauser, Qing He, Danaé Metaxa, Sorelle A. Friedler

AAAI / ACM Conference on Artificial Intelligence, Ethics, and Society · 2026

The U.S. federal government releases information about AI systems through a variety of (imperfect) transparency filings. In this project, our goals are to make it easy to search across filings, reveal how the government uses AI, and suggest improved AI transparency mechanisms.

AI and Democracy AI Governance

The Beginning of ChatGPT Ads

The Beginning of ChatGPT Ads

Emma Lurie, Ro Encarnación, Sorelle A. Friedler, Danaé Metaxa

AAAI / ACM Conference on Artificial Intelligence, Ethics, and Society · 2026

Popformer: Learning general signatures of positive selection with a self-supervised transformer

Popformer: Learning general signatures of positive selection with a self-supervised transformer

Leon Zong, Sorelle A. Friedler, Sara Mathieson

PLOS Computational Biology · 2026

Accounting for Stochasticity in Studies of Large Language Model Refusal

Accounting for Stochasticity in Studies of Large Language Model Refusal

Emma Lurie, Stephanie T. Wang, Sorelle A. Friedler, Danaé Metaxa

Non-archival Short Paper, EvalEval Workshop at ACL 2026 · 2026

Edge interventions can mitigate demographic and prestige disparities in the computer science coauthorship network

Edge interventions can mitigate demographic and prestige disparities in the computer science coauthorship network

Kate Barnes, Mia Ellis-Einhorn, Carolina Chavez, Nayera Hasan, Mohammad Fanous, Blair D. Sullivan, Sorelle Friedler, Aaron Clauset

Proceedings of the 2026 ACM Conference on Fairness, Accountability, and Transparency · 2026

Fairness and Social Networks

Do Language Models Pass the Bechdel Test Auditing Gender Biases in LLM-Generated Screenplays

Do Language Models Pass the Bechdel Test? Auditing Gender Biases in LLM-Generated Screenplays

Megha N. Govindu, Stephanie Wang, Sorelle A. Friedler, Danaé Metaxa

Proceedings of the 2026 ACM Conference on Fairness, Accountability, and Transparency · 2026

AI Auditing Fairness in Machine Learning AI and Speech

Fast algorithms to improve fair information access in networks

Fast algorithms to improve fair information access in networks

Dennis Robert Windham, Caroline J. Wendt, Alex Crane, Madelyn J. Warr, Freda Shi, Sorelle A. Friedler, Blair D. Sullivan, Aaron Clauset

PLOS Complex Systems · 2026

Fairness and Social Networks

Self-Promotion in LLM Recommendations

Self-Promotion in LLM Recommendations

Rustom M. Dubash, Sorelle A. Friedler

Forthcoming, 18th ACM Web Science Conference (WebSci) · 2026

2025

Identity-related Speech Suppression in Generative AI Content Moderation

Identity-related Speech Suppression in Generative AI Content Moderation

Grace Proebsting, Oghenefejiro Isaacs Anigboro, Charlie M. Crawford, Danaé Metaxa, Sorelle A. Friedler

Proceedings of the 5th ACM Conference on Equity and Access in Algorithms, Mechanisms, and Optimization · 2025

Best Paper Award AI Auditing AI and Speech

Feature Responsiveness Scores: Model-Agnostic Explanations for Recourse

Feature Responsiveness Scores: Model-Agnostic Explanations for Recourse

Seung Hyun Cheon, Anneke Wernerfelt, Sorelle Friedler, Berk Ustun

International Conference on Learning Representations · 2025

Interpretable Machine Learning

The OMB Artificial Intelligence Memoranda

The OMB Artificial Intelligence Memoranda

Sorelle A. Friedler, Andrew D. Selbst

Berkeley Technology Law Journal · 2025

AI and Civil Rights AI Governance

2024

Auditing GPT s Content Moderation Guardrails: Can ChatGPT Write Your Favorite TV Show

Auditing GPT's Content Moderation Guardrails: Can ChatGPT Write Your Favorite TV Show?

Yaaseen Mahomed, Charlie M. Crawford, Sanjana Gautam, Sorelle A. Friedler, Danaé Metaxa

The 2024 ACM Conference on Fairness Accountability and Transparency · 2024

AI Auditing AI and Speech

2023

Reducing Access Disparities in Networks using Edge Augmentation

Reducing Access Disparities in Networks using Edge Augmentation

Ashkan Bashardoust, Sorelle Friedler, Carlos Scheidegger, Blair D. Sullivan, Suresh Venkatasubramanian

2023 ACM Conference on Fairness Accountability and Transparency · 2023

Fairness and Social Networks

Measuring and mitigating voting access disparities: a study of race and polling locations in Florida and North Carolina

Measuring and mitigating voting access disparities: a study of race and polling locations in Florida and North Carolina

Mohsen Abbasi, Calvin Barrett, Kristian Lum, Sorelle A. Friedler, Suresh Venkatasubramanian

2023 ACM Conference on Fairness Accountability and Transparency · 2023

AI and Democracy AI and Civil Rights

Energy and Carbon Considerations of Fine-Tuning BERT

Energy and Carbon Considerations of Fine-Tuning BERT

Xiaorong Wang, Clara Na, Emma Strubell, Sorelle Friedler, Sasha Luccioni

Findings of the Association for Computational Linguistics: EMNLP 2023 · 2023

AI and the Environment

Information access representations and social capital in networks

Information access representations and social capital in networks

Ashkan Bashardoust, Hannah C. Beilinson, Sorelle A. Friedler, Jiajie Ma, Jade Rousseau, Carlos E. Scheidegger, Blair D. Sullivan, Nasanbayar Ulzii-Orshikh, Suresh Venkatasubramanian

arXiv · 2023

Fairness and Social Networks

2022

Active meta-learning for predicting and selecting perovskite crystallization experiments

Active meta-learning for predicting and selecting perovskite crystallization experiments

Venkateswaran Shekar, Gareth Nicholas, Mansoor Ani Najeeb, Margaret Zeile, Vincent Yu, …, Philip W. Nega, Emory M. Chan, Alexander J. Norquist, Joshua Schrier, Sorelle A. Friedler

The Journal of Chemical Physics · 2022

Models for understanding and quantifying feedback in societal systems

Models for understanding and quantifying feedback in societal systems

Lydia Reader, Pegah Nokhiz, Cathleen Power, Neal Patwari, Suresh Venkatasubramanian, Sorelle Friedler

2022 ACM Conference on Fairness Accountability and Transparency · 2022

Societal Feedback Mechanisms

2021

The Im possibility of fairness

The (Im)possibility of fairness

Sorelle A. Friedler, Carlos Scheidegger, Suresh Venkatasubramanian

Communications of the ACM · 2021

Fairness and Machine Learning

Shapley Residuals: Quantifying the limits of the Shapley value for explanations

Shapley Residuals: Quantifying the limits of the Shapley value for explanations

I. Elizabeth Kumar, Carlos Scheidegger, Suresh Venkatasubramanian, Sorelle A. Friedler

Neural Information Processing Systems (NeurIPS) · 2021

Interpretable Machine Learning

2020

Fairness warnings and fair-MAML: learning fairly with minimal data

Fairness warnings and fair-MAML: learning fairly with minimal data

Dylan Slack, Sorelle A. Friedler, Emile Givental

Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency · 2020

Fairness and Machine Learning

Problems with Shapley-value-based explanations as feature importance measures

Problems with Shapley-value-based explanations as feature importance measures

I. Elizabeth Kumar, Suresh Venkatasubramanian, Carlos Scheidegger, Sorelle Friedler

Proceedings of the 37th International Conference on Machine Learning · 2020

Interpretable Machine Learning

2019

Anthropogenic biases in chemical reaction data hinder exploratory inorganic synthesis

Anthropogenic biases in chemical reaction data hinder exploratory inorganic synthesis

Xiwen Jia, Allyson Lynch, Yuheng Huang, Matthew Danielson, Immaculate Lang’at, …, Aaron E. Ruby, Hao Wang, Sorelle A. Friedler, Alexander J. Norquist, Joshua Schrier

Nature · 2019

Gaps in Information Access in Social Networks

Gaps in Information Access in Social Networks

Benjamin Fish, Ashkan Bashardoust, Danah Boyd, Sorelle Friedler, Carlos Scheidegger, Suresh Venkatasubramanian

The World Wide Web Conference · 2019

Fairness and Social Networks

Fairness in representation: quantifying stereotyping as a representational harm

Fairness in representation: quantifying stereotyping as a representational harm

Mohsen Abbasi, Sorelle A. Friedler, Carlos Scheidegger, Suresh Venkatasubramanian

Proceedings of the 2019 SIAM International Conference on Data Mining · 2019

Fairness and Machine Learning

Assessing the Local Interpretability of Machine Learning Models

Assessing the Local Interpretability of Machine Learning Models

Dylan Slack, Sorelle A. Friedler, Carlos Scheidegger, Chitradeep Dutta Roy

NeurIPS Workshop on Human-Centric Machine Learning · 2019

Interpretable Machine Learning

Energy Usage Reports: Environmental awareness as part of algorithmic accountability

Energy Usage Reports: Environmental awareness as part of algorithmic accountability

Kadan Lottick, Silvia Susai, Sorelle A. Friedler, Jonathan Wilson

NeurIPS Workshop on Tackling Climate Change with Machine Learning · 2019

AI and the Environment

Fairness and Abstraction in Sociotechnical Systems

Fairness and Abstraction in Sociotechnical Systems

Andrew D. Selbst, danah boyd, Sorelle A. Friedler, Suresh Venkatasubramanian, Janet Vertesi

Proceedings of the Conference on Fairness, Accountability, and Transparency · 2019

Fairness and Machine Learning AI and Civil Rights

A comparative study of fairness-enhancing interventions in machine learning

A comparative study of fairness-enhancing interventions in machine learning

Sorelle A. Friedler, Carlos Scheidegger, Suresh Venkatasubramanian, Sonam Choudhary, Evan P. Hamilton, Derek Roth

Proceedings of the Conference on Fairness, Accountability, and Transparency · 2019

Fairness and Machine Learning

Automated Congressional Redistricting

Automated Congressional Redistricting

Harry A. Levin, Sorelle A. Friedler

ACM Journal of Experimental Algorithmics · 2019

AI and Democracy Computational Geometry

Disentangling Influence: Using disentangled representations to audit model predictions

Disentangling Influence: Using disentangled representations to audit model predictions

Charles Marx, Richard Phillips, Sorelle Friedler, Carlos Scheidegger, Suresh Venkatasubramanian

Advances in Neural Information Processing Systems · 2019

Interpretable Machine Learning

Experiment Specification, Capture and Laboratory Automation Technology ESCALATE : a software pipeline for automated chemical experimentation and data management

Experiment Specification, Capture and Laboratory Automation Technology (ESCALATE): a software pipeline for automated chemical experimentation and data management

Ian M. Pendleton, Gary Cattabriga, Zhi Li, Mansoor Ani Najeeb, Sorelle A. Friedler, Alexander J. Norquist, Emory M. Chan, Joshua Schrier

MRS Communications · 2019

2018

Decision Making with Limited Feedback: Error bounds for Recidivism Prediction and Predictive Policing

Decision Making with Limited Feedback: Error bounds for Recidivism Prediction and Predictive Policing

Danielle Ensign, Frielder Sorelle, Neville Scott, Scheidegger Carlos, Venkatasubramanian Suresh

Proceedings of Algorithmic Learning Theory · 2018

Societal Feedback Mechanisms

Interpretable Active Learning

Interpretable Active Learning

Richard Phillips, Kyu Hyun Chang, Sorelle A. Friedler

Proceedings of the 1st Conference on Fairness, Accountability and Transparency · 2018

Interpretable Machine Learning

Runaway Feedback Loops in Predictive Policing

Runaway Feedback Loops in Predictive Policing

Danielle Ensign, Sorelle A. Friedler, Scott Neville, Carlos Scheidegger, Suresh Venkatasubramanian

Proceedings of the 1st Conference on Fairness, Accountability and Transparency · 2018

AI and Civil Rights Societal Feedback Mechanisms

Auditing black-box models for indirect influence

Auditing black-box models for indirect influence

Philip Adler, Casey Falk, Sorelle A. Friedler, Tionney Nix, Gabriel Rybeck, Carlos Scheidegger, Brandon Smith, Suresh Venkatasubramanian

Knowledge and Information Systems · 2018

Best Paper Award AI Auditing Interpretable Machine Learning

2016

Principles for accountable algorithms and a social impact statement for algorithms

Principles for accountable algorithms and a social impact statement for algorithms

Nicholas Diakopoulos, Sorelle Friedler, Marcelo Arenas, Solon Barocas, Michael Hay, …, Arnaud Sahuguet, Suresh Venkatasubramanian, Christo Wilson, Cong Yu, Bendert Zevenbergen

Dagstuhl working group write-up · 2016

Hiring by Algorithm: Predicting and Preventing Disparate Impact

Hiring by Algorithm: Predicting and Preventing Disparate Impact

Ifeoma Ajunwa, Sorelle Friedler, Carlos E. Scheidegger, Suresh Venkatasubramanian

Presented at the Yale Law School Information Society Project conference Unlocking the Black Box: The Promise and Limits of Algorithmic Accountability in the Professions · 2016

Call for Papers: Special Issue on Social and Technical Trade-Offs

Call for Papers: Special Issue on Social and Technical Trade-Offs

Solon Barocas, danah boyd, Sorelle Friedler, Hanna Wallach

Big Data · 2016

Machine-learning-assisted materials discovery using failed experiments

Machine-learning-assisted materials discovery using failed experiments

Paul Raccuglia, Katherine C. Elbert, Philip D. F. Adler, Casey Falk, Malia B. Wenny, Aurelio Mollo, Matthias Zeller, Sorelle A. Friedler, Joshua Schrier, Alexander J. Norquist

Nature · 2016

AI for Science Interpretable Machine Learning

Convex Hull for Probabilistic Points

Convex Hull for Probabilistic Points

F. Betul Atalay, Sorelle A. Friedler, Dianna Xu

2016 29th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI) · 2016

Computational Geometry

2015

Certifying and Removing Disparate Impact

Certifying and Removing Disparate Impact

Michael Feldman, Sorelle A. Friedler, John Moeller, Carlos Scheidegger, Suresh Venkatasubramanian

Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · 2015

Fairness and Machine Learning AI and Civil Rights

A sensor-based framework for kinetic data compression

A sensor-based framework for kinetic data compression

Sorelle A. Friedler, David M. Mount

Computational Geometry · 2015

Computational Geometry

2013

Permissions based on wireless network data

Permissions based on wireless network data

Mohammed Waleed Kadous, Isaac Richard Taylor, Cedric Dupont, Brian Patrick Williams, Sorelle Alaina Friedler

US patent 20130244684 A1 · 2013

Position indication controls for device locations

Position indication controls for device locations

Sorelle Alaina Friedler, Mohammed Waleed Kadous, Andrew Lookingbill

US patent 20130131973 A1 (also WO 2013078125 A1) · 2013

2011

Review of pioneering women in american mathematics: the pre-1940 PhD s by Judy Green and Jeanne LaDuke

Review of pioneering women in american mathematics: the pre-1940 PhD's by Judy Green and Jeanne LaDuke

Sorelle A. Friedler

ACM SIGACT News · 2011

2010

Geometric Algorithms for Objects in Motion

Geometric Algorithms for Objects in Motion

Sorelle A. Friedler

Ph.D. thesis from University of Maryland, College Park. Dissertation committee: Prof. David Mount (chair), Prof. William Gasarch, Prof. Samir Khuller, Prof. Steven Selden, Prof. Amitabh Varshney. · 2010

Computational Geometry

Spatio-temporal Range Searching over Compressed Kinetic Sensor Data

Spatio-temporal Range Searching over Compressed Kinetic Sensor Data

Sorelle A. Friedler, David M. Mount

Lecture Notes in Computer Science · 2010

Computational Geometry

Approximation algorithm for the kinetic robust K-center problem

Approximation algorithm for the kinetic robust K-center problem

Sorelle A. Friedler, David M. Mount

Computational Geometry · 2010

Computational Geometry

2009

Compressing Kinetic Data from Sensor Networks

Compressing Kinetic Data from Sensor Networks

Sorelle A. Friedler, David M. Mount

Lecture Notes in Computer Science · 2009

Computational Geometry

2008

Enabling teachers to explore grade patterns to identify individual needs and promote fairer student assessment

Enabling teachers to explore grade patterns to identify individual needs and promote fairer student assessment

Sorelle A. Friedler, Yee Lin Tan, Nir J. Peer, Ben Shneiderman

Computers & Education · 2008