Research Papers

Large and ever-evolving technology companies continue to invest more time and resources to incorporate responsible Artificial Intelligence (AI) into production-ready systems to increase algorithmic accountability. This paper examines and seeks to offer a framework for analyzing how organizational culture and structure impact the effectiveness of responsible AI initiatives in practice. We present the results of semi-structured qualitative interviews with practitioners working in industry, investigating common challenges, ethical tensions, and effective enablers for responsible AI initiatives. Focusing on major companies developing or utilizing AI, we have mapped what organizational structures currently support or hinder responsible AI initiatives, what aspirational future processes and structures would best enable effective initiatives, and what key elements comprise the transition from current work practices to the aspirational future.

Current literature and public discourse on "trust in AI" are often focused on the principles underlying trustworthy AI, with insufficient attention paid to how people develop trust. Given that AI systems differ in their level of trustworthiness, two open questions come to the fore: how should AI trustworthiness be responsibly communicated to ensure appropriate and equitable trust judgments by different users, and how can we protect users from deceptive attempts to earn their trust? We draw from communication theories and literature on trust in technologies to develop a conceptual model called MATCH, which describes how trustworthiness is communicated in AI systems through trustworthiness cues and how those cues are processed by people to make trust judgments. Besides AI-generated content, we highlight transparency and interaction as AI systems' affordances that present a wide range of trustworthiness cues to users. By bringing to light the variety of users' cognitive processes to make trust judgments and their potential limitations, we urge technology creators to make conscious decisions in choosing reliable trustworthiness cues for target users and, as an industry, to regulate this space and prevent malicious use. Towards these goals, we define the concepts of warranted trustworthiness cues and expensive trustworthiness cues, and propose a checklist of requirements to help technology creators identify appropriate cues to use. We present a hypothetical use case to illustrate how practitioners can use MATCH to design AI systems responsibly, and discuss future directions for research and industry efforts aimed at promoting responsible trust in AI.

Organizations are rapidly deploying artificial intelligence (AI) systems to manage their workers. However, AI has been found at times to be unfair to workers. Unfairness toward workers has been associated with decreased worker effort and increased worker turnover. To avoid such problems, AI systems must be designed to support fairness and redress instances of unfairness. Despite the attention related to AI unfairness, there has not been a theoretical and systematic approach to developing a design agenda. This paper addresses the issue in three ways. First, we introduce the organizational justice theory, three different fairness types (distributive, procedural, interactional), and the frameworks for redressing instances of unfairness (retributive justice, restorative justice). Second, we review the design literature that specifically focuses on issues of AI fairness in organizations. Third, we propose a design agenda for AI fairness in organizations that applies each of the fairness types to organizational scenarios. Then, the paper concludes with implications for future research.

Explainable Artificial Intelligence (XAI) methods are typically deployed to explain and debug black-box machine learning models. However, most proposed XAI methods are black-boxes themselves and designed for images. Thus, they rely on visual interpretability to evaluate and prove explanations. In this work, we apply XAI methods previously used in the image and text-domain on time series. We present a methodology to test and evaluate various XAI methods on time series by introducing new verification techniques to incorporate the temporal dimension. We further conduct preliminary experiments to assess the quality of selected XAI method explanations with various verification methods on a range of datasets and inspecting quality metrics on it. We demonstrate that in our initial experiments, SHAP works robust for all models, but others like DeepLIFT, LRP, and Saliency Maps work better with specific architectures.

Modern artificial intelligence (AI) applications require large quantities of training and test data. This need creates critical challenges not only concerning the availability of such data, but also regarding its quality. For example, incomplete, erroneous, or inappropriate training data can lead to unreliable models that produce ultimately poor decisions. Trustworthy AI applications require high-quality training and test data along many quality dimensions, such as accuracy, completeness, and consistency. We explore empirically the relationship between six data quality dimensions and the performance of 19 popular machine learning algorithms covering the tasks of classification, regression, and clustering, with the goal of explaining their performance in terms of data quality. Our experiments distinguish three scenarios based on the AI pipeline steps that were fed with polluted data: polluted training data, test data, or both. We conclude the paper with an extensive discussion of our observations.

Much attention has focused on algorithmic audits and impact assessments to hold developers and users of algorithmic systems accountable. But existing algorithmic accountability policy approaches have neglected the lessons from non-algorithmic domains: notably, the importance of interventions that allow for the effective participation of third parties. Our paper synthesizes lessons from other fields on how to craft effective systems of external oversight for algorithmic deployments. First, we discuss the challenges of third party oversight in the current AI landscape. Second, we survey audit systems across domains - e.g., financial, environmental, and health regulation - and show that the institutional design of such audits are far from monolithic. Finally, we survey the evidence base around these design components and spell out the implications for algorithmic auditing. We conclude that the turn toward audits alone is unlikely to achieve actual algorithmic accountability, and sustained focus on institutional design will be required for meaningful third party involvement.

A series of recent developments points towards auditing as a promising mechanism to bridge the gap between principles and practice in AI ethics. Building on ongoing discussions concerning ethics-based auditing, we offer three contributions. First, we argue that ethics-based auditing can improve the quality of decision making, increase user satisfaction, unlock growth potential, enable law-making, and relieve human suffering. Second, we highlight current best practices to support the design and implementation of ethics-based auditing: To be feasible and effective, ethics-based auditing should take the form of a continuous and constructive process, approach ethical alignment from a system perspective, and be aligned with public policies and incentives for ethically desirable behaviour. Third, we identify and discuss the constraints associated with ethics-based auditing. Only by understanding and accounting for these constraints can ethics-based auditing facilitate ethical alignment of AI, while enabling society to reap the full economic and social benefits of automation.

How Do Fairness Definitions Fare? Examining Public Attitudes Towards Algorithmic Definitions of Fairness

Nripsuta Saxena, Karen Huang, Evan DeFilippis +3

What is the best way to define algorithmic fairness? While many definitions of fairness have been proposed in the computer science literature, there is no clear agreement over a particular definition. In this work, we investigate ordinary people's perceptions of three of these fairness definitions. Across two online experiments, we test which definitions people perceive to be the fairest in the context of loan decisions, and whether fairness perceptions change with the addition of sensitive information (i.e., race of the loan applicants). Overall, one definition (calibrated fairness) tends to be more preferred than the others, and the results also provide support for the principle of affirmative action.

Major depressive disorder is a debilitating disease affecting 264 million people worldwide. While many antidepressant medications are available, few clinical guidelines support choosing among them. Decision support tools (DSTs) embodying machine learning models may help improve the treatment selection process, but often fail in clinical practice due to poor system integration. We use an iterative, co-design process to investigate clinicians' perceptions of using DSTs in antidepressant treatment decisions. We identify ways in which DSTs need to engage with the healthcare sociotechnical system, including clinical processes, patient preferences, resource constraints, and domain knowledge. Our results suggest that clinical DSTs should be designed as multi-user systems that support patient-provider collaboration and offer on-demand explanations that address discrepancies between predictions and current standards of care. Through this work, we demonstrate how current trends in explainable AI may be inappropriate for clinical environments and consider paths towards designing these tools for real-world medical systems.

Ethics in AI becomes a global topic of interest for both policymakers and academic researchers. In the last few years, various research organizations, lawyers, think tankers and regulatory bodies get involved in developing AI ethics guidelines and principles. However, there is still debate about the implications of these principles. We conducted a systematic literature review (SLR) study to investigate the agreement on the significance of AI principles and identify the challenging factors that could negatively impact the adoption of AI ethics principles. The results reveal that the global convergence set consists of 22 ethical principles and 15 challenges. Transparency, privacy, accountability and fairness are identified as the most common AI ethics principles. Similarly, lack of ethical knowledge and vague principles are reported as the significant challenges for considering ethics in AI. The findings of this study are the preliminary inputs for proposing a maturity model that assess the ethical capabilities of AI systems and provide best practices for further improvements.

RE-Bench: Evaluating frontier AI R&D capabilities of language model agents against human experts

Hjalmar Wijk, Tao Lin, Joel Becker +20

Frontier AI safety policies highlight automation of AI research and development (R&D) by AI agents as an important capability to anticipate. However, there exist few evaluations for AI R&D capabilities, and none that are highly realistic and have a direct comparison to human performance. We introduce RE-Bench (Research Engineering Benchmark, v1), which consists of 7 challenging, open-ended ML research engineering environments and data from 71 8-hour attempts by 61 distinct human experts. We confirm that our experts make progress in the environments given 8 hours, with 82% of expert attempts achieving a non-zero score and 24% matching or exceeding our strong reference solutions. We compare humans to several public frontier models through best-of-k with varying time budgets and agent designs, and find that the best AI agents achieve a score 4x higher than human experts when both are given a total time budget of 2 hours per environment. However, humans currently display better returns to increasing time budgets, narrowly exceeding the top AI agent scores given an 8-hour budget, and achieving 2x the score of the top AI agent when both are given 32 total hours (across different attempts). Qualitatively, we find that modern AI agents possess significant expertise in many ML topics -- e.g. an agent wrote a faster custom Triton kernel than any of our human experts' -- and can generate and test solutions over ten times faster than humans, at much lower cost. We open-source the evaluation environments, human expert data, analysis code and agent trajectories to facilitate future research.

Benchmark datasets play a central role in the organization of machine learning research. They coordinate researchers around shared research problems and serve as a measure of progress towards shared goals. Despite the foundational role of benchmarking practices in this field, relatively little attention has been paid to the dynamics of benchmark dataset use and reuse, within or across machine learning subcommunities. In this paper, we dig into these dynamics. We study how dataset usage patterns differ across machine learning subcommunities and across time from 2015-2020. We find increasing concentration on fewer and fewer datasets within task communities, significant adoption of datasets from other tasks, and concentration across the field on datasets that have been introduced by researchers situated within a small number of elite institutions. Our results have implications for scientific evaluation, AI ethics, and equity/access within the field.