arXiv subjects

Solon Barocas

Publications and source records attributed to Solon Barocas.

At least 37 records · Page 2Linked to original sources

arXiv2025

Supporting Industry Computing Researchers in Assessing, Articulating, and Addressing the Potential Negative Societal Impact of Their Work

Recent years have witnessed increasing calls for computing researchers to grapple with the societal impacts of their work. Tools such as impact assessments have gained prominence as a method to uncover potential impacts, and a number of publication venues now encourage authors to include an impact statement in their submissions. Despite this push, little is known about the way researchers assess, articulate, and address the potential negative societal impact of their work -- especially in industry settings, where research outcomes are often quickly integrated into products. In addition, while there are nascent efforts to support researchers in this task, there remains a dearth of empirically-informed tools and processes. Through interviews with 25 industry computing researchers across different companies and research areas, we first identify four key factors that influence how they grapple with (or choose not to grapple with) the societal impact of their research. To develop an effective impact assessment template tailored to industry computing researchers' needs, we conduct an iterative co-design process with these 25 industry researchers and an additional 16 researchers and practitioners with prior experience and expertise in reviewing and developing impact assessments or broad responsible computing practices. Through the co-design process, we develop 10 design considerations to facilitate the effective design, development, and adaptation of an impact assessment template for use in industry research settings and beyond, as well as our own ``Societal Impact Assessment'' template with concrete scaffolds. We explore the effectiveness of this template through a user study with 15 industry research interns, revealing both its strengths and limitations. Finally, we discuss the implications for future researchers and organizations seeking to foster more responsible research practices.

cs.HC↗

arXiv2024

A Shared Standard for Valid Measurement of Generative AI Systems' Capabilities, Risks, and Impacts

The valid measurement of generative AI (GenAI) systems' capabilities, risks, and impacts forms the bedrock of our ability to evaluate these systems. We introduce a shared standard for valid measurement that helps place many of the disparate-seeming evaluation practices in use today on a common footing. Our framework, grounded in measurement theory from the social sciences, extends the work of Adcock & Collier (2001) in which the authors formalized valid measurement of concepts in political science via three processes: systematizing background concepts, operationalizing systematized concepts via annotation procedures, and applying those procedures to instances. We argue that valid measurement of GenAI systems' capabilities, risks, and impacts, further requires systematizing, operationalizing, and applying not only the entailed concepts, but also the contexts of interest and the metrics used. This involves both descriptive reasoning about particular instances and inferential reasoning about underlying populations, which is the purview of statistics. By placing many disparate-seeming GenAI evaluation practices on a common footing, our framework enables individual evaluations to be better understood, interrogated for reliability and validity, and meaningfully compared. This is an important step in advancing GenAI evaluation practices toward more formalized and theoretically grounded processes -- i.e., toward a science of GenAI evaluations.

cs.CY↗

arXiv2024

A Framework for Evaluating LLMs Under Task Indeterminacy

Large language model (LLM) evaluations often assume there is a single correct response -- a gold label -- for each item in the evaluation corpus. However, some tasks can be ambiguous -- i.e., they provide insufficient information to identify a unique interpretation -- or vague -- i.e., they do not clearly indicate where to draw the line when making a determination. Both ambiguity and vagueness can cause task indeterminacy -- the condition where some items in the evaluation corpus have more than one correct response. In this paper, we develop a framework for evaluating LLMs under task indeterminacy. Our framework disentangles the relationships between task specification, human ratings, and LLM responses in the LLM evaluation pipeline. Using our framework, we conduct a synthetic experiment showing that evaluations that use the "gold label" assumption underestimate the true performance. We also provide a method for estimating an error-adjusted performance interval given partial knowledge about indeterminate items in the evaluation corpus. We conclude by outlining implications of our work for the research community.

cs.LG↗

arXiv2024

Dimensions of Generative AI Evaluation Design

There are few principles or guidelines to ensure evaluations of generative AI (GenAI) models and systems are effective. To help address this gap, we propose a set of general dimensions that capture critical choices involved in GenAI evaluation design. These dimensions include the evaluation setting, the task type, the input source, the interaction style, the duration, the metric type, and the scoring method. By situating GenAI evaluations within these dimensions, we aim to guide decision-making during GenAI evaluation design and provide a structure for comparing different evaluations. We illustrate the utility of the proposed set of general dimensions using two examples: a hypothetical evaluation of the fairness of a GenAI system and three real-world GenAI evaluations of biological threats.

cs.CY↗

arXiv2024

Evaluating Generative AI Systems is a Social Science Measurement Challenge

Across academia, industry, and government, there is an increasing awareness that the measurement tasks involved in evaluating generative AI (GenAI) systems are especially difficult. We argue that these measurement tasks are highly reminiscent of measurement tasks found throughout the social sciences. With this in mind, we present a framework, grounded in measurement theory from the social sciences, for measuring concepts related to the capabilities, impacts, opportunities, and risks of GenAI systems. The framework distinguishes between four levels: the background concept, the systematized concept, the measurement instrument(s), and the instance-level measurements themselves. This four-level approach differs from the way measurement is typically done in ML, where researchers and practitioners appear to jump straight from background concepts to measurement instruments, with little to no explicit systematization in between. As well as surfacing assumptions, thereby making it easier to understand exactly what the resulting measurements do and do not mean, this framework has two important implications for evaluating evaluations: First, it can enable stakeholders from different worlds to participate in conceptual debates, broadening the expertise involved in evaluating GenAI systems. Second, it brings rigor to operational debates by offering a set of lenses for interrogating the validity of measurement instruments and their resulting measurements.

cs.CY↗

arXiv2024

The Legal Duty to Search for Less Discriminatory Algorithms

Work in computer science has established that, contrary to conventional wisdom, for a given prediction problem there are almost always multiple possible models with equivalent performance--a phenomenon often termed model multiplicity. Critically, different models of equivalent performance can produce different predictions for the same individual, and, in aggregate, exhibit different levels of impacts across demographic groups. Thus, when an algorithmic system displays a disparate impact, model multiplicity suggests that developers could discover an alternative model that performs equally well, but has less discriminatory impact. Indeed, the promise of model multiplicity is that an equally accurate, but less discriminatory algorithm (LDA) almost always exists. But without dedicated exploration, it is unlikely developers will discover potential LDAs. Model multiplicity and the availability of LDAs have significant ramifications for the legal response to discriminatory algorithms, in particular for disparate impact doctrine, which has long taken into account the availability of alternatives with less disparate effect when assessing liability. A close reading of legal authorities over the decades reveals that the law has on numerous occasions recognized that the existence of a less discriminatory alternative is sometimes relevant to a defendant's burden of justification at the second step of disparate impact analysis. Indeed, under disparate impact doctrine, it makes little sense to say that a given algorithmic system used by an employer, creditor, or housing provider is "necessary" if an equally accurate model that exhibits less disparate effect is available and possible to discover with reasonable effort. As a result, we argue that the law should place a duty of a reasonable search for LDAs on entities that develop and deploy predictive models in covered civil rights domains.

cs.CY↗

arXiv2024

Arbitrariness and Social Prediction: The Confounding Role of Variance in Fair Classification

Variance in predictions across different trained models is a significant, under-explored source of error in fair binary classification. In practice, the variance on some data examples is so large that decisions can be effectively arbitrary. To investigate this problem, we take an experimental approach and make four overarching contributions: We: 1) Define a metric called self-consistency, derived from variance, which we use as a proxy for measuring and reducing arbitrariness; 2) Develop an ensembling algorithm that abstains from classification when a prediction would be arbitrary; 3) Conduct the largest to-date empirical study of the role of variance (vis-a-vis self-consistency and arbitrariness) in fair binary classification; and, 4) Release a toolkit that makes the US Home Mortgage Disclosure Act (HMDA) datasets easily usable for future research. Altogether, our experiments reveal shocking insights about the reliability of conclusions on benchmark datasets. Most fair binary classification benchmarks are close-to-fair when taking into account the amount of arbitrariness present in predictions -- before we even try to apply any fairness interventions. This finding calls into question the practical utility of common algorithmic fairness methods, and in turn suggests that we should reconsider how we choose to measure fairness in binary classification.

cs.LG↗

arXiv2023

On the Actionability of Outcome Prediction

Predicting future outcomes is a prevalent application of machine learning in social impact domains. Examples range from predicting student success in education to predicting disease risk in healthcare. Practitioners recognize that the ultimate goal is not just to predict but to act effectively. Increasing evidence suggests that relying on outcome predictions for downstream interventions may not have desired results. In most domains there exists a multitude of possible interventions for each individual, making the challenge of taking effective action more acute. Even when causal mechanisms connecting the individual's latent states to outcomes is well understood, in any given instance (a specific student or patient), practitioners still need to infer -- from budgeted measurements of latent states -- which of many possible interventions will be most effective for this individual. With this in mind, we ask: when are accurate predictors of outcomes helpful for identifying the most suitable intervention? Through a simple model encompassing actions, latent states, and measurements, we demonstrate that pure outcome prediction rarely results in the most effective policy for taking actions, even when combined with other measurements. We find that except in cases where there is a single decisive action for improving the outcome, outcome prediction never maximizes "action value", the utility of taking actions. Making measurements of actionable latent states, where specific actions lead to desired outcomes, considerably enhances the action value compared to outcome prediction, and the degree of improvement depends on action costs and the outcome model. This analysis emphasizes the need to go beyond generic outcome prediction in interventional settings by incorporating knowledge of plausible actions and latent states.

cs.LG↗

arXiv2023

Multi-Target Multiplicity: Flexibility and Fairness in Target Specification under Resource Constraints

Prediction models have been widely adopted as the basis for decision-making in domains as diverse as employment, education, lending, and health. Yet, few real world problems readily present themselves as precisely formulated prediction tasks. In particular, there are often many reasonable target variable options. Prior work has argued that this is an important and sometimes underappreciated choice, and has also shown that target choice can have a significant impact on the fairness of the resulting model. However, the existing literature does not offer a formal framework for characterizing the extent to which target choice matters in a particular task. Our work fills this gap by drawing connections between the problem of target choice and recent work on predictive multiplicity. Specifically, we introduce a conceptual and computational framework for assessing how the choice of target affects individuals' outcomes and selection rate disparities across groups. We call this multi-target multiplicity. Along the way, we refine the study of single-target multiplicity by introducing notions of multiplicity that respect resource constraints -- a feature of many real-world tasks that is not captured by existing notions of predictive multiplicity. We apply our methods on a healthcare dataset, and show that the level of multiplicity that stems from target variable choice can be greater than that stemming from nearly-optimal models of a single target.

cs.LG↗

arXiv2023

Taxonomizing and Measuring Representational Harms: A Look at Image Tagging

In this paper, we examine computational approaches for measuring the "fairness" of image tagging systems, finding that they cluster into five distinct categories, each with its own analytic foundation. We also identify a range of normative concerns that are often collapsed under the terms "unfairness," "bias," or even "discrimination" when discussing problematic cases of image tagging. Specifically, we identify four types of representational harms that can be caused by image tagging systems, providing concrete examples of each. We then consider how different computational measurement approaches map to each of these types, demonstrating that there is not a one-to-one mapping. Our findings emphasize that no single measurement approach will be definitive and that it is not possible to infer from the use of a particular measurement approach which type of harm was intended to be measured. Lastly, equipped with this more granular understanding of the types of representational harms that can be caused by image tagging systems, we show that attempts to mitigate some of these types of harms may be in tension with one another.

cs.CY↗

arXiv2023

Informational Diversity and Affinity Bias in Team Growth Dynamics

Prior work has provided strong evidence that, within organizational settings, teams that bring a diversity of information and perspectives to a task are more effective than teams that do not. If this form of informational diversity confers performance advantages, why do we often see largely homogeneous teams in practice? One canonical argument is that the benefits of informational diversity are in tension with affinity bias. To better understand the impact of this tension on the makeup of teams, we analyze a sequential model of team formation in which individuals care about their team's performance (captured in terms of accurately predicting some future outcome based on a set of features) but experience a cost as a result of interacting with teammates who use different approaches to the prediction task. Our analysis of this simple model reveals a set of subtle behaviors that team-growth dynamics can exhibit: (i) from certain initial team compositions, they can make progress toward better performance but then get stuck partway to optimally diverse teams; while (ii) from other initial compositions, they can also move away from this optimal balance as the majority group tries to crowd out the opinions of the minority. The initial composition of the team can determine whether the dynamics will move toward or away from performance optimality, painting a path-dependent picture of inefficiencies in team compositions. Our results formalize a fundamental limitation of utility-based motivations to drive informational diversity in organizations and hint at interventions that may improve informational diversity and performance simultaneously.

cs.GT↗

arXiv2022

Mimetic Models: Ethical Implications of AI that Acts Like You

An emerging theme in artificial intelligence research is the creation of models to simulate the decisions and behavior of specific people, in domains including game-playing, text generation, and artistic expression. These models go beyond earlier approaches in the way they are tailored to individuals, and the way they are designed for interaction rather than simply the reproduction of fixed, pre-computed behaviors. We refer to these as mimetic models, and in this paper we develop a framework for characterizing the ethical and social issues raised by their growing availability. Our framework includes a number of distinct scenarios for the use of such models, and considers the impacts on a range of different participants, including the target being modeled, the operator who deploys the model, and the entities that interact with it.

cs.AI↗

arXiv2022

Measuring Representational Harms in Image Captioning

Previous work has largely considered the fairness of image captioning systems through the underspecified lens of "bias." In contrast, we present a set of techniques for measuring five types of representational harms, as well as the resulting measurements obtained for two of the most popular image captioning datasets using a state-of-the-art image captioning system. Our goal was not to audit this image captioning system, but rather to develop normatively grounded measurement techniques, in turn providing an opportunity to reflect on the many challenges involved. We propose multiple measurement techniques for each type of harm. We argue that by doing so, we are better able to capture the multi-faceted nature of each type of harm, in turn improving the (collective) validity of the resulting measurements. Throughout, we discuss the assumptions underlying our measurement approach and point out when they do not hold.

cs.CY↗

arXiv2022

REAL ML: Recognizing, Exploring, and Articulating Limitations of Machine Learning Research

Transparency around limitations can improve the scientific rigor of research, help ensure appropriate interpretation of research findings, and make research claims more credible. Despite these benefits, the machine learning (ML) research community lacks well-developed norms around disclosing and discussing limitations. To address this gap, we conduct an iterative design process with 30 ML and ML-adjacent researchers to develop and test REAL ML, a set of guided activities to help ML researchers recognize, explore, and articulate the limitations of their research. Using a three-stage interview and survey study, we identify ML researchers' perceptions of limitations, as well as the challenges they face when recognizing, exploring, and articulating limitations. We develop REAL ML to address some of these practical challenges, and highlight additional cultural challenges that will require broader shifts in community norms to address. We hope our study and REAL ML help move the ML research community toward more active and appropriate engagement with limitations.

cs.LG↗

arXiv2022

An Uncommon Task: Participatory Design in Legal AI

Despite growing calls for participation in AI design, there are to date few empirical studies of what these processes look like and how they can be structured for meaningful engagement with domain experts. In this paper, we examine a notable yet understudied AI design process in the legal domain that took place over a decade ago, the impact of which still informs legal automation efforts today. Specifically, we examine the design and evaluation activities that took place from 2006 to 2011 within the TeXT Retrieval Conference's (TREC) Legal Track, a computational research venue hosted by the National Institute of Standards and Technologies. The Legal Track of TREC is notable in the history of AI research and practice because it relied on a range of participatory approaches to facilitate the design and evaluation of new computational techniques--in this case, for automating attorney document review for civil litigation matters. Drawing on archival research and interviews with coordinators of the Legal Track of TREC, our analysis reveals how an interactive simulation methodology allowed computer scientists and lawyers to become co-designers and helped bridge the chasm between computational research and real-world, high-stakes litigation practice. In analyzing this case from the recent past, our aim is to empirically ground contemporary critiques of AI development and evaluation and the calls for greater participation as a means to address them.

cs.CY↗

arXiv2021

Better Together? How Externalities of Size Complicate Notions of Solidarity and Actuarial Fairness

Consider a cost-sharing game with players of different contribution to the total cost: an example might be an insurance company calculating premiums for a population of mixed-risk individuals. Two natural and competing notions of fairness might be to a) charge each individual the same price or b) charge each individual according to the cost that they bring to the pool. In the insurance literature, these general approaches are referred to as "solidarity" and "actuarial fairness" and are commonly viewed as opposites. However, in insurance (and many other natural settings), the cost-sharing game also exhibits "externalities of size": all else being equal, larger groups have lower average cost. In the insurance case, we analyze a model with externalities of size due to a reduction in the variability of losses. We explore how this complicates traditional understandings of fairness, drawing on literature in cooperative game theory. First, we explore solidarity: we show that it is possible for both groups (high and low risk) to strictly benefit by joining an insurance pool where costs are evenly split, as opposed to being in separate risk pools. We build on this by producing a pricing scheme that maximally subsidizes the high risk group, while maintaining an incentive for lower risk people to stay in the insurance pool. Next, we demonstrate that with this new model, the price charged to each individual has to depend on the risk of other participants, making naive actuarial fairness inefficient. Furthermore, we prove that stable pricing schemes must be ones where players have the anti-social incentive of desiring riskier partners, contradicting motivations for using actuarial fairness. Finally, we describe how these results relate to debates about fairness in machine learning and potential avenues for future research.

cs.GT↗

arXiv2021

Designing Disaggregated Evaluations of AI Systems: Choices, Considerations, and Tradeoffs

Disaggregated evaluations of AI systems, in which system performance is assessed and reported separately for different groups of people, are conceptually simple. However, their design involves a variety of choices. Some of these choices influence the results that will be obtained, and thus the conclusions that can be drawn; others influence the impacts -- both beneficial and harmful -- that a disaggregated evaluation will have on people, including the people whose data is used to conduct the evaluation. We argue that a deeper understanding of these choices will enable researchers and practitioners to design careful and conclusive disaggregated evaluations. We also argue that better documentation of these choices, along with the underlying considerations and tradeoffs that have been made, will help others when interpreting an evaluation's results and conclusions.

cs.CY↗

arXiv2021

Algorithmic Auditing and Social Justice: Lessons from the History of Audit Studies

Algorithmic audits have been embraced as tools to investigate the functioning and consequences of sociotechnical systems. Though the term is used somewhat loosely in the algorithmic context and encompasses a variety of methods, it maintains a close connection to audit studies in the social sciences--which have, for decades, used experimental methods to measure the prevalence of discrimination across domains like housing and employment. In the social sciences, audit studies originated in a strong tradition of social justice and participatory action, often involving collaboration between researchers and communities; but scholars have argued that, over time, social science audits have become somewhat distanced from these original goals and priorities. We draw from this history in order to highlight difficult tensions that have shaped the development of social science audits, and to assess their implications in the context of algorithmic auditing. In doing so, we put forth considerations to assist in the development of robust and engaged assessments of sociotechnical systems that draw from auditing's roots in racial equity and social justice.

cs.CY↗