Search

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 risk that these systems reify existing power imbalances and cause disproportionate harm to marginalized communities. Participatory approaches hold promise to instead lend agency and decision-making power to marginalized stakeholders. But existing approaches in participatory AI/ML are typically deeply grounded in context - how do we apply these approaches to foundation models, which are, by design, disconnected from context? Our paper interrogates this question. First, we examine existing attempts at incorporating participation into foundation models. We highlight the tension between participation and scale, demonstrating that it is intractable for impacted communities to meaningfully shape a foundation model that is intended to be universally applicable. In response, we develop a blueprint for participatory foundation models that identifies more local, application-oriented opportunities for meaningful participation. In addition to the "foundation" layer, our framework proposes the "subfloor'' layer, in which stakeholders develop shared technical infrastructure, norms and governance for a grounded domain, and the "surface'' layer, in which affected communities shape the use of a foundation model for a specific downstream task. The intermediate "subfloor'' layer scopes the range of potential harms to consider, and affords communities more concrete avenues for deliberation and intervention. At the same time, it avoids duplicative effort by scaling input across relevant use cases. Through three case studies in clinical care, financial services, and journalism, we illustrate how this multi-layer model can create more meaningful opportunities for participation than solely intervening at the foundation layer., Comment: 13 pages, 2 figures. Appeared at FAccT '24

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 cautionary or negative, focusing on questions like "how might LLMs be biased and how would we mitigate those biases?" This is a vital discussion: the ways in which AI generally, and LLMs specifically, can entrench biases have been well-documented. But equally vital, and much less discussed, is the more opportunity-focused counterpoint: "what promising applications do LLMs enable that could promote equity?" If LLMs are to enable a more equitable world, it is not enough just to play defense against their biases and failure modes. We must also go on offense, applying them positively to equity-enhancing use cases to increase opportunities for underserved groups and reduce societal discrimination. There are many choices which determine the impact of AI, and a fundamental choice very early in the pipeline is the problems we choose to apply it to. If we focus only later in the pipeline -- making LLMs marginally more fair as they facilitate use cases which intrinsically entrench power -- we will miss an important opportunity to guide them to equitable impacts. Here, we highlight the emerging potential of LLMs to promote equity by presenting four newly possible, promising research directions, while keeping risks and cautionary points in clear view.

We characterized the dosimetric properties of a clinical linear accelerator configured to deliver ultra-high dose rate (UHDR) irradiation to mice and cell-culture FLASH radiobiology experiments. UHDR electron beams were controlled by a microcontroller and relay interfaced with the respiratory gating system. We produced beam collimators with indexed stereotactic mouse positioning devices to provide anatomically specific preclinical treatments. Treatment delivery was monitored directly with an ionization chamber, and charge measurements were correlated with radiochromic film at the entry surface of the mice. The setup for conventional (CONV) dose rate irradiation was similar but the source-to-surface distance was longer. Monte Carlo simulations and film dosimetry were used to characterize beam properties and dose distributions. The mean electron beam energies before the flattening filter were 18.8 MeV (UHDR) and 17.7 MeV (CONV), with corresponding values at the mouse surface of 17.2 MeV and 16.2 MeV. The charges measured with an external ion chamber were linearly correlated with the mouse entrance dose. Use of relay gating for pulse control initially led to a delivery failure rate of 20% ($+/-$ 1 pulse); adjustments to account for the linac latency improved this rate to <1/20. Beam field sizes for two anatomically specific mouse collimators (4x4 $cm^2$ for whole-abdomen and 1.5x1.5 $cm^2$ for unilateral lung irradiation) were accurate within <5% and had low radiation leakage (<4%). Normalizing the dose at the center of the mouse (~0.75 cm depth) produced UHDR and CONV doses to the irradiated volumes with >95% agreement. We successfully configured a clinical linear accelerator for increased output and developed a robust preclinical platform for anatomically specific irradiation, with highly accurate and precise temporal and spatial dose delivery, for both CONV and UHDR applications., Comment: Jinghui Wang and Stavros Melemenidis are co-first authors, and Emil Sch\"uler and Peter G. Maxim are co-senior/co-corresponding authors

A broad current application of algorithms is in formal and quantitative measures of murky concepts -- like merit -- to make decisions. When people strategically respond to these sorts of evaluations in order to gain favorable decision outcomes, their behavior can be subjected to moral judgments. They may be described as 'gaming the system' or 'cheating,' or (in other cases) investing 'honest effort' or 'improving.' Machine learning literature on strategic behavior has tried to describe these dynamics by emphasizing the efforts expended by decision subjects hoping to obtain a more favorable assessment -- some works offer ways to preempt or prevent such manipulations, some differentiate 'gaming' from 'improvement' behavior, while others aim to measure the effort burden or disparate effects of classification systems. We begin from a different starting point: that the design of an evaluation itself can be understood as furthering goals held by the evaluator which may be misaligned with broader societal goals. To develop the idea that evaluation represents a strategic interaction in which both the evaluator and the subject of their evaluation are operating out of self-interest, we put forward a model that represents the process of evaluation using three interacting agents: a decision subject, an evaluator, and society, representing a bundle of values and oversight mechanisms. We highlight our model's applicability to a number of social systems where one or two players strategically undermine the others' interests to advance their own. Treating evaluators as themselves strategic allows us to re-cast the scrutiny directed at decision subjects, towards the incentives that underpin institutional designs of evaluations. The moral standing of strategic behaviors often depend on the moral standing of the evaluations and incentives that provoke such behaviors., Comment: 12 pages, 2 figures, EAAMO 2023

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., Comment: 14 pages, 3 figures

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.

To address the widespread problem of uncivil behavior, many online discussion platforms employ human moderators to take action against objectionable content, such as removing it or placing sanctions on its authors. This reactive paradigm of taking action against already-posted antisocial content is currently the most common form of moderation, and has accordingly underpinned many recent efforts at introducing automation into the moderation process. Comparatively less work has been done to understand other moderation paradigms -- such as proactively discouraging the emergence of antisocial behavior rather than reacting to it -- and the role algorithmic support can play in these paradigms. In this work, we investigate such a proactive framework for moderation in a case study of a collaborative setting: Wikipedia Talk Pages. We employ a mixed methods approach, combining qualitative and design components for a holistic analysis. Through interviews with moderators, we find that despite a lack of technical and social support, moderators already engage in a number of proactive moderation behaviors, such as preemptively intervening in conversations to keep them on track. Further, we explore how automation could assist with this existing proactive moderation workflow by building a prototype tool, presenting it to moderators, and examining how the assistance it provides might fit into their workflow. The resulting feedback uncovers both strengths and drawbacks of the prototype tool and suggests concrete steps towards further developing such assisting technology so it can most effectively support moderators in their existing proactive moderation workflow., Comment: 27 pages, 3 figures. More info at https://www.cs.cornell.edu/~cristian/Proactive_Moderation.html

In September 2021, the "One Hundred Year Study on Artificial Intelligence" project (AI100) issued the second report of its planned long-term periodic assessment of artificial intelligence (AI) and its impact on society. It was written by a panel of 17 study authors, each of whom is deeply rooted in AI research, chaired by Michael Littman of Brown University. The report, entitled "Gathering Strength, Gathering Storms," answers a set of 14 questions probing critical areas of AI development addressing the major risks and dangers of AI, its effects on society, its public perception and the future of the field. The report concludes that AI has made a major leap from the lab to people's lives in recent years, which increases the urgency to understand its potential negative effects. The questions were developed by the AI100 Standing Committee, chaired by Peter Stone of the University of Texas at Austin, consisting of a group of AI leaders with expertise in computer science, sociology, ethics, economics, and other disciplines., Comment: 82 pages, https://ai100.stanford.edu/gathering-strength-gathering-storms-one-hundred-year-study-artificial-intelligence-ai100-2021-study

The tremendous excitement around the deployment of autonomous vehicles (AVs) comes from their purported promise. In addition to decreasing accidents, AVs are projected to usher in a new era of equity in human autonomy by providing affordable, accessible, and widespread mobility for disabled, elderly, and low-income populations. However, to realize this promise, it is necessary to ensure that AVs are safe for deployment, and to contend with the risks AV technology poses, which threaten to eclipse its benefits. In this Article, we focus on an aspect of AV engineering currently unexamined in the legal literature, but with critical implications for safety, accountability, liability, and power. Specifically, we explain how understanding the fundamental engineering trade-off between accuracy and speed in AVs is critical for policymakers to regulate the uncertainty and risk inherent in AV systems. We discuss how understanding the trade-off will help create tools that will enable policymakers to assess how the trade-off is being implemented. Such tools will facilitate opportunities for developing concrete, ex ante AV safety standards and conclusive mechanisms for ex post determination of accountability after accidents occur. This will shift the balance of power from manufacturers to the public by facilitating effective regulation, reducing barriers to tort recovery, and ensuring that public values like safety and accountability are appropriately balanced., Comment: Vol. 20, pp. 249-277

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.

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.

This article surveys the use of algorithmic systems to support decision-making in the public sector. Governments adopt, procure, and use algorithmic systems to support their functions within several contexts -- including criminal justice, education, and benefits provision -- with important consequences for accountability, privacy, social inequity, and public participation in decision-making. We explore the social implications of municipal algorithmic systems across a variety of stages, including problem formulation, technology acquisition, deployment, and evaluation. We highlight several open questions that require further empirical research.

Scholars have recently drawn attention to a range of controversial issues posed by the use of computer vision for automatically generating descriptions of people in images. Despite these concerns, automated image description has become an important tool to ensure equitable access to information for blind and low vision people. In this paper, we investigate the ethical dilemmas faced by companies that have adopted the use of computer vision for producing alt text: textual descriptions of images for blind and low vision people, We use Facebook's automatic alt text tool as our primary case study. First, we analyze the policies that Facebook has adopted with respect to identity categories, such as race, gender, age, etc., and the company's decisions about whether to present these terms in alt text. We then describe an alternative -- and manual -- approach practiced in the museum community, focusing on how museums determine what to include in alt text descriptions of cultural artifacts. We compare these policies, using notable points of contrast to develop an analytic framework that characterizes the particular apprehensions behind these policy choices. We conclude by considering two strategies that seem to sidestep some of these concerns, finding that there are no easy ways to avoid the normative dilemmas posed by the use of computer vision to automate alt text.

Many policies allocate harms or benefits that are uncertain in nature: they produce distributions over the population in which individuals have different probabilities of incurring harm or benefit. Comparing different policies thus involves a comparison of their corresponding probability distributions, and we observe that in many instances the policies selected in practice are hard to explain by preferences based only on the expected value of the total harm or benefit they produce. In cases where the expected value analysis is not a sufficient explanatory framework, what would be a reasonable model for societal preferences over these distributions? Here we investigate explanations based on the framework of probability weighting from the behavioral sciences, which over several decades has identified systematic biases in how people perceive probabilities. We show that probability weighting can be used to make predictions about preferences over probabilistic distributions of harm and benefit that function quite differently from expected-value analysis, and in a number of cases provide potential explanations for policy preferences that appear hard to motivate by other means. In particular, we identify optimal policies for minimizing perceived total harm and maximizing perceived total benefit that take the distorting effects of probability weighting into account, and we discuss a number of real-world policies that resemble such allocational strategies. Our analysis does not provide specific recommendations for policy choices, but is instead fundamentally interpretive in nature, seeking to describe observed phenomena in policy choices.

Artificial intelligence (AI) is now widely used to facilitate social interaction, but its impact on social relationships and communication is not well understood. We study the social consequences of one of the most pervasive AI applications: algorithmic response suggestions ("smart replies"). Two randomized experiments (n = 1036) provide evidence that a commercially-deployed AI changes how people interact with and perceive one another in pro-social and anti-social ways. We find that using algorithmic responses increases communication efficiency, use of positive emotional language, and positive evaluations by communication partners. However, consistent with common assumptions about the negative implications of AI, people are evaluated more negatively if they are suspected to be using algorithmic responses. Thus, even though AI can increase communication efficiency and improve interpersonal perceptions, it risks changing users' language production and continues to be viewed negatively., Comment: 11 pages, 6 figures

Representativeness is a foundational yet slippery concept. Though familiar at first blush, it lacks a single precise meaning. Instead, meanings range from typical or characteristic, to a proportionate match between sample and population, to a more general sense of accuracy, generalizability, coverage, or inclusiveness. Moreover, the concept has long been contested. In statistics, debates about the merits and methods of selecting a representative sample date back to the late 19th century; in politics, debates about the value of likeness as a logic of political representation are older still. Today, as the concept crops up in the study of fairness and accountability in machine learning, we need to carefully consider the term's meanings in order to communicate clearly and account for their normative implications. In this paper, we ask what representativeness means, how it is mobilized socially, and what values and ideals it communicates or confronts. We trace the concept's history in statistics and discuss normative tensions concerning its relationship to likeness, exclusion, authority, and aspiration. We draw on these analyses to think through how representativeness is used in FAccT debates, with emphasis on data, shift, participation, and power., Comment: Accepted to ACM FAccT 2021 https://facctconference.org/2021/acceptedpapers.html

Trade-offs between accuracy and efficiency pervade law, public health, and other non-computing domains, which have developed policies to guide how to balance the two in conditions of uncertainty. While computer science also commonly studies accuracy-efficiency trade-offs, their policy implications remain poorly examined. Drawing on risk assessment practices in the US, we argue that, since examining these trade-offs has been useful for guiding governance in other domains, we need to similarly reckon with these trade-offs in governing computer systems. We focus our analysis on distributed machine learning systems. Understanding the policy implications in this area is particularly urgent because such systems, which include autonomous vehicles, tend to be high-stakes and safety-critical. We 1) describe how the trade-off takes shape for these systems, 2) highlight gaps between existing US risk assessment standards and what these systems require to be properly assessed, and 3) make specific calls to action to facilitate accountability when hypothetical risks concerning the accuracy-efficiency trade-off become realized as accidents in the real world. We close by discussing how such accountability mechanisms encourage more just, transparent governance aligned with public values.

This article provides an overview of intimate threats: a class of privacy threats that can arise within our families, romantic partnerships, close friendships, and caregiving relationships. Many common assumptions about privacy are upended in the context of these relationships, and many otherwise effective protective measures fail when applied to intimate threats. Those closest to us know the answers to our secret questions, have access to our devices, and can exercise coercive power over us. We survey a range of intimate relationships and describe their common features. Based on these features, we explore implications for both technical privacy design and policy, and offer design recommendations for ameliorating intimate privacy risks.

A recent normative turn in computer science has brought concerns about fairness, bias, and accountability to the core of the field. Yet recent scholarship has warned that much of this technical work treats problematic features of the status quo as fixed, and fails to address deeper patterns of injustice and inequality. While acknowledging these critiques, we posit that computational research has valuable roles to play in addressing social problems -- roles whose value can be recognized even from a perspective that aspires toward fundamental social change. In this paper, we articulate four such roles, through an analysis that considers the opportunities as well as the significant risks inherent in such work. Computing research can serve as a diagnostic, helping us to understand and measure social problems with precision and clarity. As a formalizer, computing shapes how social problems are explicitly defined --- changing how those problems, and possible responses to them, are understood. Computing serves as rebuttal when it illuminates the boundaries of what is possible through technical means. And computing acts as synecdoche when it makes long-standing social problems newly salient in the public eye. We offer these paths forward as modalities that leverage the particular strengths of computational work in the service of social change, without overclaiming computing's capacity to solve social problems on its own.

There has been rapidly growing interest in the use of algorithms in hiring, especially as a means to address or mitigate bias. Yet, to date, little is known about how these methods are used in practice. How are algorithmic assessments built, validated, and examined for bias? In this work, we document and analyze the claims and practices of companies offering algorithms for employment assessment. In particular, we identify vendors of algorithmic pre-employment assessments (i.e., algorithms to screen candidates), document what they have disclosed about their development and validation procedures, and evaluate their practices, focusing particularly on efforts to detect and mitigate bias. Our analysis considers both technical and legal perspectives. Technically, we consider the various choices vendors make regarding data collection and prediction targets, and explore the risks and trade-offs that these choices pose. We also discuss how algorithmic de-biasing techniques interface with, and create challenges for, antidiscrimination law.