267 citations · 710 across the 27 of their papers we have counts for
29 papers
Accounting for Stochasticity in Studies of Large Language Model Refusal
Emma Lurie, Stephanie T. Wang, Sorelle A. Friedler +1
We present preliminary empirical evidence that single-observation queries are insufficient for evaluations of LLM refusal behaviors. Using a longitudinal auditing system, we issued…
The Beginning of ChatGPT Ads
Emma Lurie, Ro Encarnación, Sorelle A. Friedler +1
This paper presents the first empirical study of advertising content being rolled out in the user-facing online interfaces of large language models (LLMs). We systematically examin…
Triangulating Across U.S. Federal AI Transparency Regimes
Emma Lurie, Emma Fauser, Qing He +2
Federal AI systems can deny benefits or flag individuals for deportation, but the public disclosures meant to make those systems visible are fragmented and unevenly detailed. This…
Do Language Models Pass the Bechdel Test? Auditing Gender Biases in LLM-Generated Screenplays
Megha N. Govindu, Stephanie T. Wang, Sorelle A. Friedler +1
As large language models (LLMs) are increasingly used in media production from journalistm to filmmaking, what impact do they have on the stories being told? Prior work has shown L…
Longitudinal Monitoring of LLM Content Moderation of Social Issues
Yunlang Dai, Emma Lurie, Danaé Metaxa +1
Large language models' (LLMs') outputs are shaped by opaque and frequently-changing company content moderation policies and practices. LLM moderation often takes the form of refusa…
Edge interventions can mitigate demographic and prestige disparities in the Computer Science coauthorship network
Kate Barnes, Mia Ellis-Einhorn, Carolina Chávez-Ruelas +5
Social factors such as demographic traits and institutional prestige structure the creation and dissemination of ideas in academic publishing. One place these effects can be observ…
Equalizing Closeness Centralities via Edge Additions
Alex Crane, Sorelle A. Friedler, Mihir Patel +3
Graph modification problems with the goal of optimizing some measure of a given node's network position have a rich history in the algorithms literature. Less commonly explored are…
Feature Responsiveness Scores: Model-Agnostic Explanations for Recourse
Harry Cheon, Anneke Wernerfelt, Sorelle A. Friedler +1
Consumer protection rules require companies that deploy models to automate decisions in high-stakes settings to explain predictions to decision subjects. These rules are motivated,…
Identity-related Speech Suppression in Generative AI Content Moderation
Grace Proebsting, Oghenefejiro Isaacs Anigboro, Charlie M. Crawford +2
Automated content moderation has long been used to help identify and filter undesired user-generated content online. But such systems have a history of incorrectly flagging content…
Fast algorithms to improve fair information access in networks
Dennis Robert Windham, Caroline J. Wendt, Alex Crane +5
We consider the problem of selecting seed nodes in a network to maximize the minimum probability of activation under an independent cascade beginning at these seeds. The motiva…
Energy and Carbon Considerations of Fine-Tuning BERT
Xiaorong Wang, Clara Na, Emma Strubell +2
Despite the popularity of the `pre-train then fine-tune' paradigm in the NLP community, existing work quantifying energy costs and associated carbon emissions has largely focused o…
Reducing Access Disparities in Networks using Edge Augmentation
Ashkan Bashardoust, Sorelle A. Friedler, Carlos E. Scheidegger +2
In social networks, a node's position is a form of \it{social capital}. Better-positioned members not only benefit from (faster) access to diverse information, but innately have mo…
Measuring and mitigating voting access disparities: a study of race and polling locations in Florida and North Carolina
Mohsen Abbasi, Suresh Venkatasubramanian, Sorelle A. Friedler +2
Voter suppression and associated racial disparities in access to voting are long-standing civil rights concerns in the United States. Barriers to voting have taken many forms over…
Information access representations and social capital in networks
Ashkan Bashardoust, Hannah C. Beilinson, Sorelle A. Friedler +6
Social network position confers power and social capital. In the setting of online social networks that have massive reach, creating mathematical representations of social capital…
Problems with Shapley-value-based explanations as feature importance measures
I. Elizabeth Kumar, Suresh Venkatasubramanian, Carlos Scheidegger +1
Game-theoretic formulations of feature importance have become popular as a way to "explain" machine learning models. These methods define a cooperative game between the features of…
Energy Usage Reports: Environmental awareness as part of algorithmic accountability
Kadan Lottick, Silvia Susai, Sorelle A. Friedler +1
The carbon footprint of algorithms must be measured and transparently reported so computer scientists can take an honest and active role in environmental sustainability. In this pa…
Fair Meta-Learning: Learning How to Learn Fairly
Dylan Slack, Sorelle Friedler, Emile Givental
Data sets for fairness relevant tasks can lack examples or be biased according to a specific label in a sensitive attribute. We demonstrate the usefulness of weight based meta-lear…
Fairness Warnings and Fair-MAML: Learning Fairly with Minimal Data
Dylan Slack, Sorelle Friedler, Emile Givental
Motivated by concerns surrounding the fairness effects of sharing and transferring fair machine learning tools, we propose two algorithms: Fairness Warnings and Fair-MAML. The firs…
Disentangling Influence: Using Disentangled Representations to Audit Model Predictions
Charles T. Marx, Richard Lanas Phillips, Sorelle A. Friedler +2
Motivated by the need to audit complex and black box models, there has been extensive research on quantifying how data features influence model predictions. Feature influence can b…
Gaps in Information Access in Social Networks
Benjamin Fish, Ashkan Bashardoust, danah boyd +3
The study of influence maximization in social networks has largely ignored disparate effects these algorithms might have on the individuals contained in the social network. Individ…
Assessing the Local Interpretability of Machine Learning Models
Dylan Slack, Sorelle A. Friedler, Carlos Scheidegger +1
The increasing adoption of machine learning tools has led to calls for accountability via model interpretability. But what does it mean for a machine learning model to be interpret…
Fairness in representation: quantifying stereotyping as a representational harm
Mohsen Abbasi, Sorelle A. Friedler, Carlos Scheidegger +1
While harms of allocation have been increasingly studied as part of the subfield of algorithmic fairness, harms of representation have received considerably less attention. In this…
A comparative study of fairness-enhancing interventions in machine learning
Sorelle A. Friedler, Carlos Scheidegger, Suresh Venkatasubramanian +3
Computers are increasingly used to make decisions that have significant impact in people's lives. Often, these predictions can affect different population subgroups disproportionat…
Interpretable Active Learning
Richard L. Phillips, Kyu Hyun Chang, Sorelle A. Friedler
Active learning has long been a topic of study in machine learning. However, as increasingly complex and opaque models have become standard practice, the process of active learning…