arXiv subjects

Sorelle A. Friedler

Publications and source records attributed to Sorelle A. Friedler.

At least 19 recordsLinked to original sources

arXiv2026

Equalizing Closeness Centralities via Edge Additions

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 modification problems with the goal of equalizing positions, though this class of problems is well-motivated from the perspective of equalizing social capital, i.e., algorithmic fairness. In this work, we study how to add edges to make the closeness centralities of a given pair of nodes more equal. We formalize several versions of this problem: Closeness Ratio Improvement, which aims to maximize the ratio of closeness centralities between two specified nodes, and Closeness Gap Minimization, which aims to minimize the absolute difference of centralities. For the former, we present a quasilinear-time $\frac{6}{11}$-approximation, complemented by a bicriteria inapproximability bound. In contrast to this positive result, we show that Closeness Gap Minimization admits no multiplicative approximation, unless P=NP. We also establish NP-hardness for All-Pairs Closeness Ratio Improvement, which aims to maximize the minimum ratio of closeness centralities across all node pairs.

cs.DS↗

arXiv2026

Accounting for Stochasticity in Studies of Large Language Model Refusal

We present preliminary empirical evidence that single-observation queries are insufficient for evaluations of LLM refusal behaviors. Using a longitudinal auditing system, we issued identical prompts 100 times each across four dates to GPT-4.1 for two socially salient topics across 20 Wikipedia sources. Refusal outcomes were consistent with a stable Bernoulli process, yet 20\% of sources fell within a decision-boundary region where a single query is largely uninformative. Reliable quantification of refusals required between 15 and 25 repeated queries, well above the single-observation standard common in existing evaluations.

cs.HC↗

arXiv2026

The Beginning of ChatGPT Ads

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 examine possible demographic differences in ad content shown to U.S. users of ChatGPT using a sock puppet audit methodology. We create and deploy 91 sock puppets in a 3x3 factorial design, using geolocation cues (account IP proxies and location-signaling prompts) to signal three racial/ethnic groups (Black, Hispanic, and White) and three income terciles (low, medium, and high). We conduct data collection starting in February 2026, collecting over 3,000 advertisements from 186 unique advertisers in response to 335 prompts on a range of realistic user queries. We find that accounts begin receiving ads 14 days after account creation, and that lower-income accounts, regardless of race, are more likely to receive ads. In this first phase of ChatGPT ads, the ads themselves skewed heavily towards consumer goods, directed users to a specific advertiser rather than a particular product, and were clearly separated from the LLM's response text, observations we anticipate will change as ads continue being integrated into LLM chat interfaces. We release a public, searchable archive of all collected advertisements. Finally, we discuss the implications of our findings, and conclude with methodological and theoretical recommendations for future empirical studies of LLM advertisements.

cs.CY↗

arXiv2026

Triangulating Across U.S. Federal AI Transparency Regimes

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 paper examines three existing U.S. federal transparency regimes---System of Records Notices (SORNs), Information Collection Requests (ICRs), and the AI Use Case Inventory---and asks how well they, individually and together, describe government AI use. We find that no single regime fully reveals how the government constructs or deploys AI: each discloses different aspects of a system, and the current disclosure infrastructure makes it very challenging for the public to track specific AI systems across regulatory regimes and over time. Persistent identifiers are absent, granularity varies widely, and the annual AI Use Case Inventory cycle means federal agencies can deploy systems months before appearing in any official record. Using hand-validated zero-shot classification and cross-document entity resolution, we contribute a triangulation method that links disclosures across all three regimes and present two case studies. Our case studies finds that linking records provides greater insight into government AI use, but even linked records would constitute insufficient oversight compared to what public reporting has revealed about the same systems. We trace each regime's disclosure weaknesses to its original administrative purpose, showing these gaps are structural, and offer recommendations focused on the AI Use Case Inventory as the mechanism best suited for public-facing transparency: (1) a broad and consistently applied AI system definition, (2) persistent system identifiers with cross-references to related disclosures, and (3) restored public visibility into risk management processes.

cs.CY↗

arXiv2026

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

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 LLMs to perpetuate social biases, including those related to gender. We complement existing literature on gender bias in LLM outputs by auditing the network structure of LLM-generated movie screenplays through automating the Bechdel test, a popular measure of women's representation in literary and film works. We also introduce the use of social network analysis measures to further analyze representational bias in LLM-generated scripts. We evaluate screenplays generated by three state-of-the-art LLMs (GPT-5, Gemini 3 Pro, and Claude Sonnet 4.5) against 768 corresponding human-written screenplays, finding that human-written scripts are more likely to pass the Bechdel test. However, other network analyses, like centrality, homophily, and triadic relationships demonstrate that in some cases LLM-scripts have less bias, although all script types demonstrate some representational bias under most measures. We conclude by discussing the continued need for further quantitative assessments of media representations and AI-generated content.

cs.HC↗

arXiv2025

Feature Responsiveness Scores: Model-Agnostic Explanations for Recourse

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, in part, by the belief that explanations can promote recourse by revealing information that decision subjects can use to contest or overturn their predictions. In practice, companies provide individuals with a list of principal reasons based on feature importance derived from methods like SHAP and LIME. In this work, we show how common practices can fail to provide recourse and propose to highlight features based on their responsiveness -- the probability that a decision subject can attain a target prediction through an arbitrary intervention on the feature. We develop efficient methods to compute responsiveness scores for any model and actionability constraints. We show that standard practices in lending can undermine decision subjects by highlighting unresponsive features and explaining predictions that are fixed.

stat.ML↗

arXiv2025

Longitudinal Monitoring of LLM Content Moderation of Social Issues

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 refusal; models' refusal to produce text about certain topics both reflects company policy and subtly shapes public discourse. We introduce AI Watchman, a longitudinal auditing system to publicly measure and track LLM refusals over time, to provide transparency into an important and black-box aspect of LLMs. Using a dataset of over 400 social issues, we audit Open AI's moderation endpoint, GPT-4.1, and GPT-5, and DeepSeek (both in English and Chinese). We find evidence that changes in company policies, even those not publicly announced, can be detected by AI Watchman, and identify company- and model-specific differences in content moderation. We also qualitatively analyze and categorize different forms of refusal. This work contributes evidence for the value of longitudinal auditing of LLMs, and AI Watchman, one system for doing so.

cs.CL↗

arXiv2025

Identity-related Speech Suppression in Generative AI Content Moderation

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 by and about marginalized identities for removal. Generative AI systems now use such filters to keep undesired generated content from being created by or shown to users. While a lot of focus has been given to making sure such systems do not produce undesired outcomes, considerably less attention has been paid to making sure appropriate text can be generated. From classrooms to Hollywood, as generative AI is increasingly used for creative or expressive text generation, whose stories will these technologies allow to be told, and whose will they suppress? In this paper, we define and introduce measures of speech suppression, focusing on speech related to different identity groups incorrectly filtered by a range of content moderation APIs. Using both short-form, user-generated datasets traditional in content moderation and longer generative AI-focused data, including two datasets we introduce in this work, we create a benchmark for measurement of speech suppression for nine identity groups. Across one traditional and four generative AI-focused automated content moderation services tested, we find that identity-related speech is more likely to be incorrectly suppressed than other speech. We find that reasons for incorrect flagging behavior vary by identity based on stereotypes and text associations, with, e.g., disability-related content more likely to be flagged for self-harm or health-related reasons while non-Christian content is more likely to be flagged as violent or hateful. As generative AI systems are increasingly used for creative work, we urge further attention to how this may impact the creation of identity-related content.

cs.CL↗

arXiv2025

Fast algorithms to improve fair information access in networks

We consider the problem of selecting $k$ seed nodes in a network to maximize the minimum probability of activation under an independent cascade beginning at these seeds. The motivation is to promote fairness by ensuring that even the least advantaged members of the network have good access to information. Our problem can be viewed as a variant of the classic influence maximization objective, but it appears somewhat more difficult to solve: only heuristics are known. Moreover, the scalability of these methods is sharply constrained by the need to repeatedly estimate access probabilities. We design and evaluate a suite of $10$ new scalable algorithms which crucially do not require probability estimation. To facilitate comparison with the state-of-the-art, we make three more contributions which may be of broader interest. We introduce a principled method of selecting a pairwise information transmission parameter used in experimental evaluations, as well as a new performance metric which allows for comparison of algorithms across a range of values for the parameter $k$. Finally, we provide a new benchmark corpus of $174$ networks drawn from $6$ domains. Our algorithms retain most of the performance of the state-of-the-art while reducing running time by orders of magnitude. Specifically, a meta-learner approach is on average only $20\%$ less effective than the state-of-the-art on held-out data, but about $75-130$ times faster. Further, the meta-learner's performance exceeds the state-of the-art on about $20\%$ of networks, and the magnitude of its running time advantage is maintained on much larger networks.

cs.SI↗

arXiv2023

Information access representations and social capital in networks

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 is an important step towards understanding how network position can differentially confer advantage to different groups and how network position can itself be a source of advantage. In this paper, we use well established models for information flow on networks as a base to propose a formal descriptor of the network position of a node as represented by its information access. Combining these descriptors allows a full representation of social capital across the network. Using real-world networks, we demonstrate that this representation allows the identification of differences between groups based on network specific measures of inequality of access.

cs.SI↗

arXiv2022

Reducing Access Disparities in Networks using Edge Augmentation

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 more potential influence on information spread. Structural biases often arise from network formation, and can lead to significant disparities in information access based on position. Further, processes such as link recommendation can exacerbate this inequality by relying on network structure to augment connectivity. We argue that one can understand and quantify this social capital through the lens of information flow in the network. We consider the setting where all nodes may be sources of distinct information, and a node's (dis)advantage deems its ability to access all information available on the network. We introduce three new measures of advantage (broadcast, influence, and control), which are quantified in terms of position in the network using \it{access signatures} -- vectors that represent a node's ability to share information. We then consider the problem of improving equity by making interventions to increase the access of the least-advantaged nodes. We argue that edge augmentation is most appropriate for mitigating bias in the network structure, and frame a budgeted intervention problem for maximizing minimum pairwise access. Finally, we propose heuristic strategies for selecting edge augmentations and empirically evaluate their performance on a corpus of real-world social networks. We demonstrate that a small number of interventions significantly increase the broadcast measure of access for the least-advantaged nodes (over 5 times more than random), and also improve the minimum influence. Additional analysis shows that these interventions can also dramatically shrink the gap in advantage between nodes (over \%82) and reduce disparities between their access signatures.

cs.SI↗

arXiv2022

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

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 the decades. A history of violent explicit discouragement has shifted to more subtle access limitations that can include long lines and wait times, long travel times to reach a polling station, and other logistical barriers to voting. Our focus in this work is on quantifying disparities in voting access pertaining to the overall time-to-vote, and how they could be remedied via a better choice of polling location or provisioning more sites where voters can cast ballots. However, appropriately calibrating access disparities is difficult because of the need to account for factors such as population density and different community expectations for reasonable travel times. In this paper, we quantify access to polling locations, developing a methodology for the calibrated measurement of racial disparities in polling location "load" and distance to polling locations. We apply this methodology to a study of real-world data from Florida and North Carolina to identify disparities in voting access from the 2020 election. We also introduce algorithms, with modifications to handle scale, that can reduce these disparities by suggesting new polling locations from a given list of identified public locations (including schools and libraries). Applying these algorithms on the 2020 election location data also helps to expose and explore tradeoffs between the cost of allocating more polling locations and the potential impact on access disparities. The developed voting access measurement methodology and algorithmic remediation technique is a first step in better polling location assignment.

cs.CY↗

arXiv2019

Energy Usage Reports: Environmental awareness as part of algorithmic accountability

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 paper, we take analyses usually applied at the industrial level and make them accessible for individual computer science researchers with an easy-to-use Python package. Localizing to the energy mixture of the electrical power grid, we make the conversion from energy usage to CO2 emissions, in addition to contextualizing these results with more human-understandable benchmarks such as automobile miles driven. We also include comparisons with energy mixtures employed in electrical grids around the world. We propose including these automatically-generated Energy Usage Reports as part of standard algorithmic accountability practices, and demonstrate the use of these reports as part of model-choice in a machine learning context.

cs.LG↗

arXiv2019

Assessing the Local Interpretability of Machine Learning Models

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 interpretable by humans, and how can this be assessed? We focus on two definitions of interpretability that have been introduced in the machine learning literature: simulatability (a user's ability to run a model on a given input) and "what if" local explainability (a user's ability to correctly determine a model's prediction under local changes to the input, given knowledge of the model's original prediction). Through a user study with 1,000 participants, we test whether humans perform well on tasks that mimic the definitions of simulatability and "what if" local explainability on models that are typically considered locally interpretable. To track the relative interpretability of models, we employ a simple metric, the runtime operation count on the simulatability task. We find evidence that as the number of operations increases, participant accuracy on the local interpretability tasks decreases. In addition, this evidence is consistent with the common intuition that decision trees and logistic regression models are interpretable and are more interpretable than neural networks.

cs.LG↗

arXiv2019

Disentangling Influence: Using Disentangled Representations to Audit Model Predictions

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 be direct (a direct influence on model outcomes) and indirect (model outcomes are influenced via proxy features). Feature influence can also be expressed in aggregate over the training or test data or locally with respect to a single point. Current research has typically focused on one of each of these dimensions. In this paper, we develop disentangled influence audits, a procedure to audit the indirect influence of features. Specifically, we show that disentangled representations provide a mechanism to identify proxy features in the dataset, while allowing an explicit computation of feature influence on either individual outcomes or aggregate-level outcomes. We show through both theory and experiments that disentangled influence audits can both detect proxy features and show, for each individual or in aggregate, which of these proxy features affects the classifier being audited the most. In this respect, our method is more powerful than existing methods for ascertaining feature influence.

cs.LG↗

arXiv2019

Gaps in Information Access in Social Networks

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. Individuals may place a high value on receiving information, e.g. job openings or advertisements for loans. While well-connected individuals at the center of the network are likely to receive the information that is being distributed through the network, poorly connected individuals are systematically less likely to receive the information, producing a gap in access to the information between individuals. In this work, we study how best to spread information in a social network while minimizing this access gap. We propose to use the maximin social welfare function as an objective function, where we maximize the minimum probability of receiving the information under an intervention. We prove that in this setting this welfare function constrains the access gap whereas maximizing the expected number of nodes reached does not. We also investigate the difficulties of using the maximin, and present hardness results and analysis for standard greedy strategies. Finally, we investigate practical ways of optimizing for the maximin, and give empirical evidence that a simple greedy-based strategy works well in practice.

cs.SI↗

arXiv2019

Fairness in representation: quantifying stereotyping as a representational harm

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 paper, we formalize two notions of stereotyping and show how they manifest in later allocative harms within the machine learning pipeline. We also propose mitigation strategies and demonstrate their effectiveness on synthetic datasets.

cs.LG↗

arXiv2018

Interpretable Active Learning

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, too, has become more opaque. There has been little investigation into interpreting what specific trends and patterns an active learning strategy may be exploring. This work expands on the Local Interpretable Model-agnostic Explanations framework (LIME) to provide explanations for active learning recommendations. We demonstrate how LIME can be used to generate locally faithful explanations for an active learning strategy, and how these explanations can be used to understand how different models and datasets explore a problem space over time. In order to quantify the per-subgroup differences in how an active learning strategy queries spatial regions, we introduce a notion of uncertainty bias (based on disparate impact) to measure the discrepancy in the confidence for a model's predictions between one subgroup and another. Using the uncertainty bias measure, we show that our query explanations accurately reflect the subgroup focus of the active learning queries, allowing for an interpretable explanation of what is being learned as points with similar sources of uncertainty have their uncertainty bias resolved. We demonstrate that this technique can be applied to track uncertainty bias over user-defined clusters or automatically generated clusters based on the source of uncertainty.

stat.ML↗