Hoda Heidari

Amanda Coston, Anna Kawakami, Haiyi Zhu et al. · cmu

Recent research increasingly brings to question the appropriateness of using predictive tools in complex, real-world tasks. While a growing body of work has explored ways to improve value alignment in these tools, comparatively less work has centered concerns around the fundamental justifiability of using these tools. This work seeks to center validity considerations in deliberations around whether and how to build data-driven algorithms in high-stakes domains. Toward this end, we translate key concepts from validity theory to predictive algorithms. We apply the lens of validity to re-examine common challenges in problem formulation and data issues that jeopardize the justifiability of using predictive algorithms and connect these challenges to the social science discourse around validity. Our interdisciplinary exposition clarifies how these concepts apply to algorithmic decision making contexts. We demonstrate how these validity considerations could distill into a series of high-level questions intended to promote and document reflections on the legitimacy of the predictive task and the suitability of the data.

Valerie Chen, Umang Bhatt, Hoda Heidari et al. · cambridge, cmu

Machine learning (ML) practitioners are increasingly tasked with developing models that are aligned with non-technical experts' values and goals. However, there has been insufficient consideration on how practitioners should translate domain expertise into ML updates. In this paper, we consider how to capture interactions between practitioners and experts systematically. We devise a taxonomy to match expert feedback types with practitioner updates. A practitioner may receive feedback from an expert at the observation- or domain-level, and convert this feedback into updates to the dataset, loss function, or parameter space. We review existing work from ML and human-computer interaction to describe this feedback-update taxonomy, and highlight the insufficient consideration given to incorporating feedback from non-technical experts. We end with a set of open questions that naturally arise from our proposed taxonomy and subsequent survey.

Michael Feffer, Nikolas Martelaro, Hoda Heidari · cmu

Prior work has established the importance of integrating AI ethics topics into computer and data sciences curricula. We provide evidence suggesting that one of the critical objectives of AI Ethics education must be to raise awareness of AI harms. While there are various sources to learn about such harms, The AI Incident Database (AIID) is one of the few attempts at offering a relatively comprehensive database indexing prior instances of harms or near harms stemming from the deployment of AI technologies in the real world. This study assesses the effectiveness of AIID as an educational tool to raise awareness regarding the prevalence and severity of AI harms in socially high-stakes domains. We present findings obtained through a classroom study conducted at an R1 institution as part of a course focused on the societal and ethical considerations around AI and ML. Our qualitative findings characterize students' initial perceptions of core topics in AI ethics and their desire to close the educational gap between their technical skills and their ability to think systematically about ethical and societal aspects of their work. We find that interacting with the database helps students better understand the magnitude and severity of AI harms and instills in them a sense of urgency around (a) designing functional and safe AI and (b) strengthening governance and accountability mechanisms. Finally, we compile students' feedback about the tool and our class activity into actionable recommendations for the database development team and the broader community to improve awareness of AI harms in AI ethics education.

Benjamin Laufer, Jon Kleinberg, Hoda Heidari

Recent advances in Machine Learning (ML) and Artificial Intelligence (AI) follow a familiar structure: A firm releases a large, pretrained model. It is designed to be adapted and tweaked by other entities to perform particular, domain-specific functions. The model is described as `general-purpose,' meaning it can be transferred to a wide range of downstream tasks, in a process known as adaptation or fine-tuning. Understanding this process - the strategies, incentives, and interactions involved in the development of AI tools - is crucial for making conclusions about societal implications and regulatory responses, and may provide insights beyond AI about general-purpose technologies. We propose a model of this adaptation process. A Generalist brings the technology to a certain level of performance, and one or more Domain specialist(s) adapt it for use in particular domain(s). Players incur costs when they invest in the technology, so they need to reach a bargaining agreement on how to share the resulting revenue before making their investment decisions. We find that for a broad class of cost and revenue functions, there exists a set of Pareto-optimal profit-sharing arrangements where the players jointly contribute to the technology. Our analysis, which utilizes methods based on bargaining solutions and sub-game perfect equilibria, provides insights into the strategic behaviors of firms in these types of interactions. For example, profit-sharing can arise even when one firm faces significantly higher costs than another. After demonstrating findings in the case of one domain-specialist, we provide closed-form and numerical bargaining solutions in the generalized setting with $n$ domain specialists. We find that any potential domain specialization will either contribute, free-ride, or abstain in their uptake of the technology, and provide conditions yielding these different responses.

Anna Kawakami, Amanda Coston, Haiyi Zhu et al. · cmu

AI-based decision-making tools are rapidly spreading across a range of real-world, complex domains like healthcare, criminal justice, and child welfare. A growing body of research has called for increased scrutiny around the validity of AI system designs. However, in real-world settings, it is often not possible to fully address questions around the validity of an AI tool without also considering the design of associated organizational and public policies. Yet, considerations around how an AI tool may interface with policy are often only discussed retrospectively, after the tool is designed or deployed. In this short position paper, we discuss opportunities to promote multi-stakeholder deliberations around the design of AI-based technologies and associated policies, at the earliest stages of a new project.

Rachel M. Kim, Blaine Kuehnert, Alice Lai et al.

As Artificial Intelligence (AI) systems proliferate, the need for systematic, transparent, and actionable processes for evaluating them is growing. While many resources exist to support AI evaluation, they have several limitations. Few address both the process of designing, developing, and deploying an AI system and the outcomes it produces. Furthermore, few are end-to-end and operational, give actionable guidance, or present evidence of usability or effectiveness in practice. In this paper, we introduce a third-party AI assurance framework that addresses these gaps. We focus on third-party assurance to prevent conflict of interest and ensure credibility and accountability of the process. We begin by distinguishing assurance from audits in several key dimensions. Then, following design principles, we reflect on the shortcomings of existing resources to identify a set of design requirements for AI assurance. We then construct a prototype of an assurance process that consists of (1) a responsibility assignment matrix to determine the different levels of involvement each stakeholder has at each stage of the AI lifecycle, (2) an interview protocol for each stakeholder of an AI system, (3) a maturity matrix to assess AI systems' adherence to best practices, and (4) a template for an assurance report that draws from more mature assurance practices in business accounting. We conduct early validation of our AI assurance framework by applying the framework to two distinct AI use cases -- a business document tagging tool for downstream processing in a large private firm, and a housing resource allocation tool in a public agency -- and conducting six expert validation interviews. Our findings show early evidence that our AI assurance framework is sound and comprehensive, usable across different organizational contexts, and effective at identifying bespoke issues with AI systems.

Hoda Heidari, Solon Barocas, Jon Kleinberg et al.

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.

Alex John London, Hoda Heidari

The prevailing discourse around AI ethics lacks the language and formalism necessary to capture the diverse ethical concerns that emerge when AI systems interact with individuals. Drawing on Sen and Nussbaum's capability approach, we present a framework formalizing a network of ethical concepts and entitlements necessary for AI systems to confer meaningful benefit or assistance to stakeholders. Such systems enhance stakeholders' ability to advance their life plans and well-being while upholding their fundamental rights. We characterize two necessary conditions for morally permissible interactions between AI systems and those impacted by their functioning, and two sufficient conditions for realizing the ideal of meaningful benefit. We then contrast this ideal with several salient failure modes, namely, forms of social interactions that constitute unjustified paternalism, coercion, deception, exploitation and domination. The proliferation of incidents involving AI in high-stakes domains underscores the gravity of these issues and the imperative to take an ethics-led approach to AI systems from their inception.

Emily Black, Rakshit Naidu, Rayid Ghani et al.

While algorithmic fairness is a thriving area of research, in practice, mitigating issues of bias often gets reduced to enforcing an arbitrarily chosen fairness metric, either by enforcing fairness constraints during the optimization step, post-processing model outputs, or by manipulating the training data. Recent work has called on the ML community to take a more holistic approach to tackle fairness issues by systematically investigating the many design choices made through the ML pipeline, and identifying interventions that target the issue's root cause, as opposed to its symptoms. While we share the conviction that this pipeline-based approach is the most appropriate for combating algorithmic unfairness on the ground, we believe there are currently very few methods of \emph{operationalizing} this approach in practice. Drawing on our experience as educators and practitioners, we first demonstrate that without clear guidelines and toolkits, even individuals with specialized ML knowledge find it challenging to hypothesize how various design choices influence model behavior. We then consult the fair-ML literature to understand the progress to date toward operationalizing the pipeline-aware approach: we systematically collect and organize the prior work that attempts to detect, measure, and mitigate various sources of unfairness through the ML pipeline. We utilize this extensive categorization of previous contributions to sketch a research agenda for the community. We hope this work serves as the stepping stone toward a more comprehensive set of resources for ML researchers, practitioners, and students interested in exploring, designing, and testing pipeline-oriented approaches to algorithmic fairness.

Nil-Jana Akpinar, Manish Nagireddy, Logan Stapleton et al.

Motivated by the growing importance of reducing unfairness in ML predictions, Fair-ML researchers have presented an extensive suite of algorithmic 'fairness-enhancing' remedies. Most existing algorithms, however, are agnostic to the sources of the observed unfairness. As a result, the literature currently lacks guiding frameworks to specify conditions under which each algorithmic intervention can potentially alleviate the underpinning cause of unfairness. To close this gap, we scrutinize the underlying biases (e.g., in the training data or design choices) that cause observational unfairness. We present the conceptual idea and a first implementation of a bias-injection sandbox tool to investigate fairness consequences of various biases and assess the effectiveness of algorithmic remedies in the presence of specific types of bias. We call this process the bias(stress)-testing of algorithmic interventions. Unlike existing toolkits, ours provides a controlled environment to counterfactually inject biases in the ML pipeline. This stylized setup offers the distinct capability of testing fairness interventions beyond observational data and against an unbiased benchmark. In particular, we can test whether a given remedy can alleviate the injected bias by comparing the predictions resulting after the intervention in the biased setting with true labels in the unbiased regime-that is, before any bias injection. We illustrate the utility of our toolkit via a proof-of-concept case study on synthetic data. Our empirical analysis showcases the type of insights that can be obtained through our simulations.

Shivani Kapania, William Agnew, Motahhare Eslami et al.

The recent excitement around generative models has sparked a wave of proposals suggesting the replacement of human participation and labor in research and development--e.g., through surveys, experiments, and interviews--with synthetic research data generated by large language models (LLMs). We conducted interviews with 19 qualitative researchers to understand their perspectives on this paradigm shift. Initially skeptical, researchers were surprised to see similar narratives emerge in the LLM-generated data when using the interview probe. However, over several conversational turns, they went on to identify fundamental limitations, such as how LLMs foreclose participants' consent and agency, produce responses lacking in palpability and contextual depth, and risk delegitimizing qualitative research methods. We argue that the use of LLMs as proxies for participants enacts the surrogate effect, raising ethical and epistemological concerns that extend beyond the technical limitations of current models to the core of whether LLMs fit within qualitative ways of knowing.

Charvi Rastogi, Liu Leqi, Kenneth Holstein et al.

Hybrid human-ML systems increasingly make consequential decisions in a wide range of domains. These systems are often introduced with the expectation that the combined human-ML system will achieve complementary performance, that is, the combined decision-making system will be an improvement compared with either decision-making agent in isolation. However, empirical results have been mixed, and existing research rarely articulates the sources and mechanisms by which complementary performance is expected to arise. Our goal in this work is to provide conceptual tools to advance the way researchers reason and communicate about human-ML complementarity. Drawing upon prior literature in human psychology, machine learning, and human-computer interaction, we propose a taxonomy characterizing distinct ways in which human and ML-based decision-making can differ. In doing so, we conceptually map potential mechanisms by which combining human and ML decision-making may yield complementary performance, developing a language for the research community to reason about design of hybrid systems in any decision-making domain. To illustrate how our taxonomy can be used to investigate complementarity, we provide a mathematical aggregation framework to examine enabling conditions for complementarity. Through synthetic simulations, we demonstrate how this framework can be used to explore specific aspects of our taxonomy and shed light on the optimal mechanisms for combining human-ML judgments

Ningjing Tang, Megan Li, Amy Winecoff et al.

Model documentation plays a crucial role in promoting transparency and responsible development of AI systems. With the rise of Generative AI (GenAI), open-source platforms have increasingly become hubs for hosting and distributing these models, prompting platforms like Hugging Face to develop dedicated model documentation guidelines that align with responsible AI principles. Despite these growing efforts, there remains a lack of understanding of how developers document their GenAI models on open-source platforms. Through interviews with 13 GenAI developers active on open-source platforms, we provide empirical insights into their documentation practices and challenges. Our analysis reveals that despite existing resources, developers of GenAI models still face multiple layers of uncertainties in their model documentation: (1) uncertainties about what specific content should be included; (2) uncertainties about how to effectively report key components of their models; and (3) uncertainties in deciding who should take responsibilities for various aspects of model documentation. Based on our findings, we discuss the implications for policymakers, open-source platforms, and the research community to support meaningful, effective and actionable model documentation in the GenAI era, including cultivating better community norms, building robust evaluation infrastructures, and clarifying roles and responsibilities.

Kyle Boerstler, Vijay Keswani, Lok Chan et al.

Preference elicitation frameworks feature heavily in the research on participatory ethical AI tools and provide a viable mechanism to enquire and incorporate the moral values of various stakeholders. As part of the elicitation process, surveys about moral preferences, opinions, and judgments are typically administered only once to each participant. This methodological practice is reasonable if participants' responses are stable over time such that, all other relevant factors being held constant, their responses today will be the same as their responses to the same questions at a later time. However, we do not know how often that is the case. It is possible that participants' true moral preferences change, are subject to temporary moods or whims, or are influenced by environmental factors we don't track. If participants' moral responses are unstable in such ways, it would raise important methodological and theoretical issues for how participants' true moral preferences, opinions, and judgments can be ascertained. We address this possibility here by asking the same survey participants the same moral questions about which patient should receive a kidney when only one is available ten times in ten different sessions over two weeks, varying only presentation order across sessions. We measured how often participants gave different responses to simple (Study One) and more complicated (Study Two) repeated scenarios. On average, the fraction of times participants changed their responses to controversial scenarios was around 10-18% across studies, and this instability is observed to have positive associations with response time and decision-making difficulty. We discuss the implications of these results for the efficacy of moral preference elicitation, highlighting the role of response instability in causing value misalignment between stakeholders and AI tools trained on their moral judgments.

Vijay Keswani, Vincent Conitzer, Hoda Heidari et al.

Computational preference elicitation methods are tools used to learn people's preferences quantitatively in a given context. Recent works on preference elicitation advocate for active learning as an efficient method to iteratively construct queries (framed as comparisons between context-specific cases) that are likely to be most informative about an agent's underlying preferences. In this work, we argue that the use of active learning for moral preference elicitation relies on certain assumptions about the underlying moral preferences, which can be violated in practice. Specifically, we highlight the following common assumptions (a) preferences are stable over time and not sensitive to the sequence of presented queries, (b) the appropriate hypothesis class is chosen to model moral preferences, and (c) noise in the agent's responses is limited. While these assumptions can be appropriate for preference elicitation in certain domains, prior research on moral psychology suggests they may not be valid for moral judgments. Through a synthetic simulation of preferences that violate the above assumptions, we observe that active learning can have similar or worse performance than a basic random query selection method in certain settings. Yet, simulation results also demonstrate that active learning can still be viable if the degree of instability or noise is relatively small and when the agent's preferences can be approximately represented with the hypothesis class used for learning. Our study highlights the nuances associated with effective moral preference elicitation in practice and advocates for the cautious use of active learning as a methodology to learn moral preferences.

Ningjing Tang, Alice Qian, Qiaosi Wang et al.

Content Warning: This paper contains participant quotes and discussions related to mental health challenges, emotional distress, and suicidal ideation. Large language models (LLMs) are increasingly used for mental health support, yet the model safeguards -- particularly refusals to engage with sensitive content -- remain poorly understood from the perspectives of users and mental health professionals (MHPs) and have been reported to cause real-world harms. This paper presents findings from a sequential mixed-methods study examining how LLM refusals are experienced and interpreted in mental health support interactions. Through surveys (N=53) and in-depth interviews (N=16) with individuals using LLMs for mental health support and MHPs, we reveal that refusals are not isolated, single-turn system behaviors but rather constitute dynamic, multi-phase experiences: pre-refusal expectation formation, refusal triggering and encounter, refusal message framing, resource referral provision, and post-refusal outcomes. We contribute a multi-phase framework for evaluating refusals beyond binary policy compliance accuracy and design recommendations for future refusal mechanisms. These findings suggest that understanding LLM refusals requires moving beyond single-turn interactions toward recognizing them as holistic experiences embedded within users' support-seeking trajectories and the broader LLM design pipeline.

Vijay Keswani, Cyrus Cousins, Breanna Nguyen et al.

Alignment methods in moral domains seek to elicit moral preferences of human stakeholders and incorporate them into AI. This presupposes moral preferences as static targets, but such preferences often evolve over time. Proper alignment of AI to dynamic human preferences should ideally account for "legitimate" changes to moral reasoning, while ignoring changes related to attention deficits, cognitive biases, or other arbitrary factors. However, common AI alignment approaches largely neglect temporal changes in preferences, posing serious challenges to proper alignment, especially in high-stakes applications of AI, e.g., in healthcare domains, where misalignment can jeopardize the trustworthiness of the system and yield serious individual and societal harms. This work investigates the extent to which people's moral preferences change over time, and the impact of such changes on AI alignment. Our study is grounded in the kidney allocation domain, where we elicit responses to pairwise comparisons of hypothetical kidney transplant patients from over 400 participants across 3-5 sessions. We find that, on average, participants change their response to the same scenario presented at different times around 6-20% of the time (exhibiting "response instability"). Additionally, we observe significant shifts in several participants' retrofitted decision-making models over time (capturing "model instability"). The predictive performance of simple AI models decreases as a function of both response and model instability. Moreover, predictive performance diminishes over time, highlighting the importance of accounting for temporal changes in preferences during training. These findings raise fundamental normative and technical challenges relevant to AI alignment, highlighting the need to better understand the object of alignment (what to align to) when user preferences change significantly over time.

Blaine Kuehnert, Nari Johnson, Ravit Dotan et al.

Documentation-based disclosure has become a central governance strategy for responsible AI, particularly in public-sector procurement. Tools such as model cards, datasheets, and AI FactSheets are increasingly expected to support accountability, risk assessment, and informed decision-making across organizational boundaries. Yet there is limited empirical evidence about how these artifacts are produced, interpreted, and used in practice. In this paper, we present a qualitative study of the GovAI Coalition FactSheet, a widely adopted transparency document designed to support AI procurement and governance in government contexts. Drawing on semi-structured interviews with vendors and public-sector practitioners, alongside a systematic analysis of completed FactSheets, we examine how FactSheets are used, what information they surface, and where they fall short. We find that FactSheets are asked to serve multiple and conflicting purposes simultaneously: showcasing vendor offerings, supporting evaluation and due diligence, and facilitating early-stage dialogue between vendors and agencies. These competing expectations, combined with the structural constraints of voluntary and public self-disclosure, limit the ability of FactSheets to function as standalone evaluation or risk-assessment tools. At the same time, our findings suggest that when understood as relational artifacts used to establish trust, shared understanding, and ongoing dialogue, FactSheets can help create conditions that support more meaningful disclosure and governance over time.

Megan Li, Wendy Bickersteth, Ningjing Tang et al.

Due to its general-purpose nature, Generative AI is applied in an ever-growing set of domains and tasks, leading to an expanding set of risks of harm impacting people, communities, society, and the environment. These risks may arise due to failures during the design and development of the technology, as well as during its release, deployment, or downstream usages and appropriations of its outputs. In this paper, building on prior taxonomies of AI risks, harms, and failures, we construct a taxonomy specifically for Generative AI failures and map them to the harms they precipitate. Through a systematic analysis of 499 publicly reported incidents, we describe what harms are reported, how they arose, and who they impact. We report the prevalence of each type of harm, underlying failure mode, and harmed stakeholder, as well as their common co-occurrences. We find that most reported incidents are caused by use-related issues but bring harm to parties beyond the end user(s) of the Generative AI system at fault, and that the landscape of Generative AI harms is distinct from that of traditional AI. Our work offers actionable insights to policymakers, developers, and Generative AI users. In particular, we call for the prioritization of non-technical risk and harm mitigation strategies, including public disclosures and education and careful regulatory stances.

Tori Qiu, Benjamin Laufer, Jon Kleinberg et al.

Regulatory frameworks, such as the EU AI Act, encourage openness of general-purpose AI models by offering legal exemptions for "open-source" models. Despite this legislative attention on openness, the definition of open-source foundation models remains ambiguous. This paper models the strategic interactions among the creator of a general-purpose model (the generalist) and the entity that fine-tunes the general-purpose model to a specialized domain or task (the specialist), in response to regulatory requirements on model openness. We present a stylized model of the regulator's choice of an open-source definition to evaluate which AI openness standards will establish appropriate economic incentives for developers. Our results characterize market equilibria -- specifically, upstream model release decisions and downstream fine-tuning efforts -- under various openness regulations and present a range of effective regulatory penalties and open-source thresholds. Overall, we find the model's baseline performance determines when increasing the regulatory penalty vs. the open-source threshold will significantly alter the generalist's release strategy. Our model provides a theoretical foundation for AI governance decisions around openness and enables evaluation and refinement of practical open-source policies.

Mateo Dulce Rubio, Siqi Zeng, Qi Wang et al.

Landmines remain a threat to war-affected communities for years after conflicts have ended, partly due to the laborious nature of demining tasks. Humanitarian demining operations begin by collecting relevant information from the sites to be cleared, which is then analyzed by human experts to determine the potential risk of remaining landmines. In this paper, we propose RELand system to support these tasks, which consists of three major components. We (1) provide general feature engineering and label assigning guidelines to enhance datasets for landmine risk modeling, which are widely applicable to global demining routines, (2) formulate landmine presence as a classification problem and design a novel interpretable model based on sparse feature masking and invariant risk minimization, and run extensive evaluation under proper protocols that resemble real-world demining operations to show a significant improvement over the state-of-the-art, and (3) build an interactive web interface to suggest priority areas for demining organizations. We are currently collaborating with a humanitarian demining NGO in Colombia that is using our system as part of their field operations in two areas recently prioritized for demining.

Nari Johnson, Deepthi Sudharsan, Hamna et al.

Measurement is essential to improving AI performance and mitigating harms for marginalized groups. As generative AI systems are rapidly deployed across geographies and contexts, AI measurement practices must be designed to support repeatable, automatable application across different models, datasets, and evaluation settings. But the drive to automate measurement can be in tension with the ability for measurement instruments to capture the expertise and perspectives of communities impacted by AI. Recent work advocates for breaking measurement into several key stages: first moving from an abstract concept to be measured into a precise, "systematized" concept; next operationalizing the systematized concept into a concrete measurement instrument; and finally applying the measurement instrument on data to produce measurements. This opens up an opportunity to concentrate community engagement in the systematization phase before operationalizing and applying measurement instruments. In this paper, we explore how to involve communities in systematizing the concept of "cultural appropriateness" in text-to-image models' representation of culturally significant artifacts through case studies with three communities: blind and low vision individuals residing in the UK, residents of Kerala, and residents of Tamil Nadu. Our systematized concepts reflect community members' lived experiences interacting with each artifact and how they want their material culture to be depicted, demonstrating the value of community involvement in defining valid measures. We explore how these systematized concepts can be operationalized into automated measurement instruments that could be applied using a multimodal LLM-as-a-judge approach and challenges that remain. We reflect on the benefits and limitations of such approaches.

Nari Johnson, Hoda Heidari

Artificial Intelligence Impact Assessments ("AIIAs"), a family of tools that provide structured processes to imagine the possible impacts of a proposed AI system, have become an increasingly popular proposal to govern AI systems. Recent efforts from government or private-sector organizations have proposed many diverse instantiations of AIIAs, which take a variety of forms ranging from open-ended questionnaires to graded score-cards. However, to date that has been limited evaluation of existing AIIA instruments. We conduct a classroom study (N = 38) at a large research-intensive university (R1) in an elective course focused on the societal and ethical implications of AI. We assign students to different organizational roles (for example, an ML scientist or product manager) and ask participant teams to complete one of three existing AI impact assessments for one of two imagined generative AI systems. In our thematic analysis of participants' responses to pre- and post-activity questionnaires, we find preliminary evidence that impact assessments can influence participants' perceptions of the potential risks of generative AI systems, and the level of responsibility held by AI experts in addressing potential harm. We also discover a consistent set of limitations shared by several existing AIIA instruments, which we group into concerns about their format and content, as well as the feasibility and effectiveness of the activity in foreseeing and mitigating potential harms. Drawing on the findings of this study, we provide recommendations for future work on developing and validating AIIAs.

Michael Feffer, Anusha Sinha, Wesley Hanwen Deng et al.

In response to rising concerns surrounding the safety, security, and trustworthiness of Generative AI (GenAI) models, practitioners and regulators alike have pointed to AI red-teaming as a key component of their strategies for identifying and mitigating these risks. However, despite AI red-teaming's central role in policy discussions and corporate messaging, significant questions remain about what precisely it means, what role it can play in regulation, and how it relates to conventional red-teaming practices as originally conceived in the field of cybersecurity. In this work, we identify recent cases of red-teaming activities in the AI industry and conduct an extensive survey of relevant research literature to characterize the scope, structure, and criteria for AI red-teaming practices. Our analysis reveals that prior methods and practices of AI red-teaming diverge along several axes, including the purpose of the activity (which is often vague), the artifact under evaluation, the setting in which the activity is conducted (e.g., actors, resources, and methods), and the resulting decisions it informs (e.g., reporting, disclosure, and mitigation). In light of our findings, we argue that while red-teaming may be a valuable big-tent idea for characterizing GenAI harm mitigations, and that industry may effectively apply red-teaming and other strategies behind closed doors to safeguard AI, gestures towards red-teaming (based on public definitions) as a panacea for every possible risk verge on security theater. To move toward a more robust toolbox of evaluations for generative AI, we synthesize our recommendations into a question bank meant to guide and scaffold future AI red-teaming practices.

Yoshua Bengio, Sören Mindermann, Daniel Privitera et al. · eth-zurich, mit

The first International AI Safety Report comprehensively synthesizes the current evidence on the capabilities, risks, and safety of advanced AI systems. The report was mandated by the nations attending the AI Safety Summit in Bletchley, UK. Thirty nations, the UN, the OECD, and the EU each nominated a representative to the report's Expert Advisory Panel. A total of 100 AI experts contributed, representing diverse perspectives and disciplines. Led by the report's Chair, these independent experts collectively had full discretion over the report's content.

Yoshua Bengio, Sören Mindermann, Daniel Privitera et al. · eth-zurich

This is the interim publication of the first International Scientific Report on the Safety of Advanced AI. The report synthesises the scientific understanding of general-purpose AI -- AI that can perform a wide variety of tasks -- with a focus on understanding and managing its risks. A diverse group of 75 AI experts contributed to this report, including an international Expert Advisory Panel nominated by 30 countries, the EU, and the UN. Led by the Chair, these independent experts collectively had full discretion over the report's content. The final report is available at arXiv:2501.17805

Anna Kawakami, Amanda Coston, Hoda Heidari et al. · cmu

As public sector agencies rapidly introduce new AI tools in high-stakes domains like social services, it becomes critical to understand how decisions to adopt these tools are made in practice. We borrow from the anthropological practice to ``study up'' those in positions of power, and reorient our study of public sector AI around those who have the power and responsibility to make decisions about the role that AI tools will play in their agency. Through semi-structured interviews and design activities with 16 agency decision-makers, we examine how decisions about AI design and adoption are influenced by their interactions with and assumptions about other actors within these agencies (e.g., frontline workers and agency leaders), as well as those above (legal systems and contracted companies), and below (impacted communities). By centering these networks of power relations, our findings shed light on how infrastructural, legal, and social factors create barriers and disincentives to the involvement of a broader range of stakeholders in decisions about AI design and adoption. Agency decision-makers desired more practical support for stakeholder involvement around public sector AI to help overcome the knowledge and power differentials they perceived between them and other stakeholders (e.g., frontline workers and impacted community members). Building on these findings, we discuss implications for future research and policy around actualizing participatory AI approaches in public sector contexts.

Megan Li, Wendy Bickersteth, Ningjing Tang et al.

Despite growing concerns about the risks of Generative AI (GenAI), there is limited understanding of public perceptions of these risks and their associated failure modes -- defined as recurring patterns of sociotechnical breakdown across the GenAI lifecycle that contribute to risks of real-world harm. To address this gap, we present a survey instrument, validated with eight subject matter experts and deployed on a sample of 960 U.S.-based participants, to assess awareness and perceptions of GenAI's failure modes, their associated risks, and stakeholder responsibilities to address them. To support realism and content validity, our instrument is structured around scenarios grounded in publicly reported incidents and a taxonomy of GenAI's failure modes. Findings suggest that our instrument is (1) effective for assessing risk awareness and perceptions in a way that is grounded in people's current contexts of use, yet is extensible to new contexts that will inevitably arise; and (2) potentially useful for informing the design of AI literacy tools and interventions. We argue for AI literacy and governance approaches that align with how people encounter and reason about GenAI in everyday life.

Benjamin Laufer, Jon Kleinberg, Hoda Heidari

Recent policy proposals aim to improve the safety of general-purpose AI, but there is little understanding of the efficacy of different regulatory approaches to AI safety. We present a strategic model that explores the interactions between safety regulation, the general-purpose AI creators, and domain specialists--those who adapt the technology for specific applications. Our analysis examines how different regulatory measures, targeting different parts of the AI development chain, affect the outcome of this game. In particular, we assume AI technology is characterized by two key attributes: safety and performance. The regulator first sets a minimum safety standard that applies to one or both players, with strict penalties for non-compliance. The general-purpose creator then invests in the technology, establishing its initial safety and performance levels. Next, domain specialists refine the AI for their specific use cases, updating the safety and performance levels and taking the product to market. The resulting revenue is then distributed between the specialist and generalist through a revenue-sharing parameter. Our analysis reveals two key insights: First, weak safety regulation imposed predominantly on domain specialists can backfire. While it might seem logical to regulate AI use cases, our analysis shows that weak regulations targeting domain specialists alone can unintentionally reduce safety. This effect persists across a wide range of settings. Second, in sharp contrast to the previous finding, we observe that stronger, well-placed regulation can in fact mutually benefit all players subjected to it. When regulators impose appropriate safety standards on both general-purpose AI creators and domain specialists, the regulation functions as a commitment device, leading to safety and performance gains, surpassing what is achieved under no regulation or regulating one player alone.

Sophie Greenwood, Karen Levy, Solon Barocas et al.

As AI technologies improve, people are increasingly willing to delegate tasks to AI agents. In many cases, the human decision-maker chooses whether to delegate to an AI agent based on properties of the specific instance of the decision-making problem they are facing. Since humans typically lack full awareness of all the factors relevant to this choice for a given decision-making instance, they perform a kind of categorization by treating indistinguishable instances -- those that have the same observable features -- as the same. In this paper, we define the problem of designing the optimal algorithmic delegate in the presence of categories. This is an important dimension in the design of algorithms to work with humans, since we show that the optimal delegate can be an arbitrarily better teammate than the optimal standalone algorithmic agent. The solution to this optimal delegation problem is not obvious: we discover that this problem is fundamentally combinatorial, and illustrate the complex relationship between the optimal design and the properties of the decision-making task even in simple settings. Indeed, we show that finding the optimal delegate is computationally hard in general. However, we are able to find efficient algorithms for producing the optimal delegate in several broad cases of the problem, including when the optimal action may be decomposed into functions of features observed by the human and the algorithm. Finally, we run computational experiments to simulate a designer updating an algorithmic delegate over time to be optimized for when it is actually adopted by users, and show that while this process does not recover the optimal delegate in general, the resulting delegate often performs quite well.

Vijay Keswani, Vincent Conitzer, Walter Sinnott-Armstrong et al.

A growing body of work in Ethical AI attempts to capture human moral judgments through simple computational models. The key question we address in this work is whether such simple AI models capture {the critical} nuances of moral decision-making by focusing on the use case of kidney allocation. We conducted twenty interviews where participants explained their rationale for their judgments about who should receive a kidney. We observe participants: (a) value patients' morally-relevant attributes to different degrees; (b) use diverse decision-making processes, citing heuristics to reduce decision complexity; (c) can change their opinions; (d) sometimes lack confidence in their decisions (e.g., due to incomplete information); and (e) express enthusiasm and concern regarding AI assisting humans in kidney allocation decisions. Based on these findings, we discuss challenges of computationally modeling moral judgments {as a stand-in for human input}, highlight drawbacks of current approaches, and suggest future directions to address these issues.

Cyrus Cousins, Vijay Keswani, Vincent Conitzer et al.

Recent AI work trends towards incorporating human-centric objectives, with the explicit goal of aligning AI models to personal preferences and societal values. Using standard preference elicitation methods, researchers and practitioners build models of human decisions and judgments, which are then used to align AI behavior with that of humans. However, models commonly used in such elicitation processes often do not capture the true cognitive processes of human decision making, such as when people use heuristics to simplify information associated with a decision problem. As a result, models learned from people's decisions often do not align with their cognitive processes, and can not be used to validate the learning framework for generalization to other decision-making tasks. To address this limitation, we take an axiomatic approach to learning cognitively faithful decision processes from pairwise comparisons. Building on the vast literature characterizing the cognitive processes that contribute to human decision-making, and recent work characterizing such processes in pairwise comparison tasks, we define a class of models in which individual features are first processed and compared across alternatives, and then the processed features are then aggregated via a fixed rule, such as the Bradley-Terry rule. This structured processing of information ensures such models are realistic and feasible candidates to represent underlying human decision-making processes. We demonstrate the efficacy of this modeling approach in learning interpretable models of human decision making in a kidney allocation task, and show that our proposed models match or surpass the accuracy of prior models of human pairwise decision-making.

Kimberly Le Truong, Riccardo Fogliato, Hoda Heidari et al.

Current benchmarks for evaluating Large Language Models (LLMs) often do not exhibit enough writing style diversity, with many adhering primarily to standardized conventions. Such benchmarks do not fully capture the rich variety of communication patterns exhibited by humans. Thus, it is possible that LLMs, which are optimized on these benchmarks, may demonstrate brittle performance when faced with "non-standard" input. In this work, we test this hypothesis by rewriting evaluation prompts using persona-based LLM prompting, a low-cost method to emulate diverse writing styles. Our results show that, even with identical semantic content, variations in writing style and prompt formatting significantly impact the estimated performance of the LLM under evaluation. Notably, we identify distinct writing styles that consistently trigger either low or high performance across a range of models and tasks, irrespective of model family, size, and recency. Our work offers a scalable approach to augment existing benchmarks, improving the external validity of the assessments they provide for measuring LLM performance across linguistic variations.

Nari Johnson, Elise Silva, Harrison Leon et al.

Most AI tools adopted by governments are not developed internally, but instead are acquired from third-party vendors in a process called public procurement. In this paper, we conduct the first empirical study of how United States cities' procurement practices shape critical decisions surrounding public sector AI. We conduct semi-structured interviews with 19 city employees who oversee AI procurement across 7 U.S. cities. We found that cities' legacy procurement practices, which are shaped by decades-old laws and norms, establish infrastructure that determines which AI is purchased, and which actors hold decision-making power over procured AI. We characterize the emerging actions cities have taken to adapt their purchasing practices to address algorithmic harms. From employees' reflections on real-world AI procurements, we identify three key challenges that motivate but are not fully addressed by existing AI procurement reform initiatives. Based on these findings, we discuss implications and opportunities for the FAccT community to support cities in foreseeing and preventing AI harms throughout the public procurement processes.

Anusha Sinha, Keltin Grimes, James Lucassen et al.

A red team simulates adversary attacks to help defenders find effective strategies to defend their systems in a real-world operational setting. As more enterprise systems adopt AI, red-teaming will need to evolve to address the unique vulnerabilities and risks posed by AI systems. We take the position that AI systems can be more effectively red-teamed if AI red-teaming is recognized as a domain-specific evolution of cyber red-teaming. Specifically, we argue that existing Cyber Red Teams who adopt this framing will be able to better evaluate systems with AI components by recognizing that AI poses new risks, has new failure modes to exploit, and often contains unpatchable bugs that re-prioritize disclosure and mitigation strategies. Similarly, adopting a cybersecurity framing will allow existing AI Red Teams to leverage a well-tested structure to emulate realistic adversaries, promote mutual accountability with formal rules of engagement, and provide a pattern to mature the tooling necessary for repeatable, scalable engagements. In these ways, the merging of AI and Cyber Red Teams will create a robust security ecosystem and best position the community to adapt to the rapidly changing threat landscape.

Joshua Nathaniel Williams, Anurag Katakkar, Hoda Heidari et al. · cmu

Counterfactual explanations have been a popular method of post-hoc explainability for a variety of settings in Machine Learning. Such methods focus on explaining classifiers by generating new data points that are similar to a given reference, while receiving a more desirable prediction. In this work, we investigate a framing for counterfactual generation methods that considers counterfactuals not as independent draws from a region around the reference, but as jointly sampled with the reference from the underlying data distribution. Through this framing, we derive a distance metric, tailored for counterfactual similarity that can be applied to a broad range of settings. Through both quantitative and qualitative analyses of counterfactual generation methods, we show that this framing allows us to express more nuanced dependencies among the covariates.

Michael Feffer, Hoda Heidari, Zachary C. Lipton

With Artificial Intelligence systems increasingly applied in consequential domains, researchers have begun to ask how these systems ought to act in ethically charged situations where even humans lack consensus. In the Moral Machine project, researchers crowdsourced answers to "Trolley Problems" concerning autonomous vehicles. Subsequently, Noothigattu et al. (2018) proposed inferring linear functions that approximate each individual's preferences and aggregating these linear models by averaging parameters across the population. In this paper, we examine this averaging mechanism, focusing on fairness concerns in the presence of strategic effects. We investigate a simple setting where the population consists of two groups, with the minority constituting an α < 0.5 share of the population. To simplify the analysis, we consider the extreme case in which within-group preferences are homogeneous. Focusing on the fraction of contested cases where the minority group prevails, we make the following observations: (a) even when all parties report their preferences truthfully, the fraction of disputes where the minority prevails is less than proportionate in α; (b) the degree of sub-proportionality grows more severe as the level of disagreement between the groups increases; (c) when parties report preferences strategically, pure strategy equilibria do not always exist; and (d) whenever a pure strategy equilibrium exists, the majority group prevails 100% of the time. These findings raise concerns about stability and fairness of preference vector averaging as a mechanism for aggregating diverging voices. Finally, we discuss alternatives, including randomized dictatorship and median-based mechanisms.

Keegan Harris, Valerie Chen, Joon Sik Kim et al.

When subjected to automated decision-making, decision subjects may strategically modify their observable features in ways they believe will maximize their chances of receiving a favorable decision. In many practical situations, the underlying assessment rule is deliberately kept secret to avoid gaming and maintain competitive advantage. The resulting opacity forces the decision subjects to rely on incomplete information when making strategic feature modifications. We capture such settings as a game of Bayesian persuasion, in which the decision maker offers a form of recourse to the decision subject by providing them with an action recommendation (or signal) to incentivize them to modify their features in desirable ways. We show that when using persuasion, the decision maker and decision subject are never worse off in expectation, while the decision maker can be significantly better off. While the decision maker's problem of finding the optimal Bayesian incentive-compatible (BIC) signaling policy takes the form of optimization over infinitely-many variables, we show that this optimization can be cast as a linear program over finitely-many regions of the space of possible assessment rules. While this reformulation simplifies the problem dramatically, solving the linear program requires reasoning about exponentially-many variables, even in relatively simple cases. Motivated by this observation, we provide a polynomial-time approximation scheme that recovers a near-optimal signaling policy. Finally, our numerical simulations on semi-synthetic data empirically demonstrate the benefits of using persuasion in the algorithmic recourse setting.

Keegan Harris, Daniel Ngo, Logan Stapleton et al.

In settings where Machine Learning (ML) algorithms automate or inform consequential decisions about people, individual decision subjects are often incentivized to strategically modify their observable attributes to receive more favorable predictions. As a result, the distribution the assessment rule is trained on may differ from the one it operates on in deployment. While such distribution shifts, in general, can hinder accurate predictions, our work identifies a unique opportunity associated with shifts due to strategic responses: We show that we can use strategic responses effectively to recover causal relationships between the observable features and outcomes we wish to predict, even under the presence of unobserved confounding variables. Specifically, our work establishes a novel connection between strategic responses to ML models and instrumental variable (IV) regression by observing that the sequence of deployed models can be viewed as an instrument that affects agents' observable features but does not directly influence their outcomes. We show that our causal recovery method can be utilized to improve decision-making across several important criteria: individual fairness, agent outcomes, and predictive risk. In particular, we show that if decision subjects differ in their ability to modify non-causal attributes, any decision rule deviating from the causal coefficients can lead to (potentially unbounded) individual-level unfairness.

Keegan Harris, Hoda Heidari, Zhiwei Steven Wu

Automated decision-making tools increasingly assess individuals to determine if they qualify for high-stakes opportunities. A recent line of research investigates how strategic agents may respond to such scoring tools to receive favorable assessments. While prior work has focused on the short-term strategic interactions between a decision-making institution (modeled as a principal) and individual decision-subjects (modeled as agents), we investigate interactions spanning multiple time-steps. In particular, we consider settings in which the agent's effort investment today can accumulate over time in the form of an internal state - impacting both his future rewards and that of the principal. We characterize the Stackelberg equilibrium of the resulting game and provide novel algorithms for computing it. Our analysis reveals several intriguing insights about the role of multiple interactions in shaping the game's outcome: First, we establish that in our stateful setting, the class of all linear assessment policies remains as powerful as the larger class of all monotonic assessment policies. While recovering the principal's optimal policy requires solving a non-convex optimization problem, we provide polynomial-time algorithms for recovering both the principal and agent's optimal policies under common assumptions about the process by which effort investments convert to observable features. Most importantly, we show that with multiple rounds of interaction at her disposal, the principal is more effective at incentivizing the agent to accumulate effort in her desired direction. Our work addresses several critical gaps in the growing literature on the societal impacts of automated decision-making - by focusing on longer time horizons and accounting for the compounding nature of decisions individuals receive over time.

David Lindner, Hoda Heidari, Andreas Krause

Machine Learning (ML) increasingly informs the allocation of opportunities to individuals and communities in areas such as lending, education, employment, and beyond. Such decisions often impact their subjects' future characteristics and capabilities in an a priori unknown fashion. The decision-maker, therefore, faces exploration-exploitation dilemmas akin to those in multi-armed bandits. Following prior work, we model communities as arms. To capture the long-term effects of ML-based allocation decisions, we study a setting in which the reward from each arm evolves every time the decision-maker pulls that arm. We focus on reward functions that are initially increasing in the number of pulls but may become (and remain) decreasing after a certain point. We argue that an acceptable sequential allocation of opportunities must take an arm's potential for growth into account. We capture these considerations through the notion of policy regret, a much stronger notion than the often-studied external regret, and present an algorithm with provably sub-linear policy regret for sufficiently long time horizons. We empirically compare our algorithm with several baselines and find that it consistently outperforms them, in particular for long time horizons.

Mohammad Yaghini, Andreas Krause, Hoda Heidari

Existing mathematical notions of fairness fail to account for the context of decision-making. We argue that moral consideration of contextual factors is an inherently human task. So we present a framework to learn context-aware mathematical formulations of fairness by eliciting people's situated fairness assessments. Our family of fairness notions corresponds to a new interpretation of economic models of Equality of Opportunity (EOP), and it includes most existing notions of fairness as special cases. Our human-in-the-loop approach is designed to learn the appropriate parameters of the EOP family by utilizing human responses to pair-wise questions about decision subjects' circumstance and deservingness, and the harm/benefit imposed on them. We illustrate our framework in a hypothetical criminal risk assessment scenario by conducting a series of human-subject experiments on Amazon Mechanical Turk. Our work takes an important initial step toward empowering stakeholders to have a voice in the formulation of fairness for Machine Learning.

Hoda Heidari, Vedant Nanda, Krishna P. Gummadi

Most existing notions of algorithmic fairness are one-shot: they ensure some form of allocative equality at the time of decision making, but do not account for the adverse impact of the algorithmic decisions today on the long-term welfare and prosperity of certain segments of the population. We take a broader perspective on algorithmic fairness. We propose an effort-based measure of fairness and present a data-driven framework for characterizing the long-term impact of algorithmic policies on reshaping the underlying population. Motivated by the psychological literature on \emph{social learning} and the economic literature on equality of opportunity, we propose a micro-scale model of how individuals may respond to decision-making algorithms. We employ existing measures of segregation from sociology and economics to quantify the resulting macro-scale population-level change. Importantly, we observe that different models may shift the group-conditional distribution of qualifications in different directions. Our findings raise a number of important questions regarding the formalization of fairness for decision-making models.

Hoda Heidari, Michele Loi, Krishna P. Gummadi et al.

We map the recently proposed notions of algorithmic fairness to economic models of Equality of opportunity (EOP)---an extensively studied ideal of fairness in political philosophy. We formally show that through our conceptual mapping, many existing definition of algorithmic fairness, such as predictive value parity and equality of odds, can be interpreted as special cases of EOP. In this respect, our work serves as a unifying moral framework for understanding existing notions of algorithmic fairness. Most importantly, this framework allows us to explicitly spell out the moral assumptions underlying each notion of fairness, and interpret recent fairness impossibility results in a new light. Last but not least and inspired by luck egalitarian models of EOP, we propose a new family of measures for algorithmic fairness. We illustrate our proposal empirically and show that employing a measure of algorithmic (un)fairness when its underlying moral assumptions are not satisfied, can have devastating consequences for the disadvantaged group's welfare.

Till Speicher, Hoda Heidari, Nina Grgic-Hlaca et al.

Discrimination via algorithmic decision making has received considerable attention. Prior work largely focuses on defining conditions for fairness, but does not define satisfactory measures of algorithmic unfairness. In this paper, we focus on the following question: Given two unfair algorithms, how should we determine which of the two is more unfair? Our core idea is to use existing inequality indices from economics to measure how unequally the outcomes of an algorithm benefit different individuals or groups in a population. Our work offers a justified and general framework to compare and contrast the (un)fairness of algorithmic predictors. This unifying approach enables us to quantify unfairness both at the individual and the group level. Further, our work reveals overlooked tradeoffs between different fairness notions: using our proposed measures, the overall individual-level unfairness of an algorithm can be decomposed into a between-group and a within-group component. Earlier methods are typically designed to tackle only between-group unfairness, which may be justified for legal or other reasons. However, we demonstrate that minimizing exclusively the between-group component may, in fact, increase the within-group, and hence the overall unfairness. We characterize and illustrate the tradeoffs between our measures of (un)fairness and the prediction accuracy.

Hoda Heidari, Claudio Ferrari, Krishna P. Gummadi et al.

We draw attention to an important, yet largely overlooked aspect of evaluating fairness for automated decision making systems---namely risk and welfare considerations. Our proposed family of measures corresponds to the long-established formulations of cardinal social welfare in economics, and is justified by the Rawlsian conception of fairness behind a veil of ignorance. The convex formulation of our welfare-based measures of fairness allows us to integrate them as a constraint into any convex loss minimization pipeline. Our empirical analysis reveals interesting trade-offs between our proposal and (a) prediction accuracy, (b) group discrimination, and (c) Dwork et al.'s notion of individual fairness. Furthermore and perhaps most importantly, our work provides both heuristic justification and empirical evidence suggesting that a lower-bound on our measures often leads to bounded inequality in algorithmic outcomes; hence presenting the first computationally feasible mechanism for bounding individual-level inequality.

Richard Berk, Hoda Heidari, Shahin Jabbari et al.

We introduce a flexible family of fairness regularizers for (linear and logistic) regression problems. These regularizers all enjoy convexity, permitting fast optimization, and they span the rang from notions of group fairness to strong individual fairness. By varying the weight on the fairness regularizer, we can compute the efficient frontier of the accuracy-fairness trade-off on any given dataset, and we measure the severity of this trade-off via a numerical quantity we call the Price of Fairness (PoF). The centerpiece of our results is an extensive comparative study of the PoF across six different datasets in which fairness is a primary consideration.

Richard A. Berk, Hoda Heidari, Shahin Jabbari et al.

Objectives: Discussions of fairness in criminal justice risk assessments typically lack conceptual precision. Rhetoric too often substitutes for careful analysis. In this paper, we seek to clarify the tradeoffs between different kinds of fairness and between fairness and accuracy. Methods: We draw on the existing literatures in criminology, computer science and statistics to provide an integrated examination of fairness and accuracy in criminal justice risk assessments. We also provide an empirical illustration using data from arraignments. Results: We show that there are at least six kinds of fairness, some of which are incompatible with one another and with accuracy. Conclusions: Except in trivial cases, it is impossible to maximize accuracy and fairness at the same time, and impossible simultaneously to satisfy all kinds of fairness. In practice, a major complication is different base rates across different legally protected groups. There is a need to consider challenging tradeoffs.