The present study aims to extend research on the role of values for the perceived legitimacy of legal authorities by focusing on (1) supranational legal authorities and (2) a broad range of values. We examine how (alignment between) people’s personal values and their perception of the values of the European Union (EU) are related to perceived legitimacy of the Court of Justice of the EU (CJEU) and the EU more broadly. Inspired by moral foundations theory, we distinguish between individualizing (...) (i.e., “democracy”, “liberty”, and “fairness”) and binding values (i.e., “rule of law”, “respect for national authority”, and “respect for tradition”). An online survey was conducted in six EU member states (N = 1,136). A factor analysis confirmed a two-factor model (individualizing vs. binding values) for both personal values and perceived EU values. Four regression models were run for each of the value factors, including personal values, perceived EU values, and their interaction, on each of the outcomes (i.e., perceived CJEU and EU legitimacy). Perceived endorsement by the EU of both individualizing and binding values predicted higher legitimacy perceptions of the CJEU and EU. Furthermore, personal binding values had a negative effect on perceived EU legitimacy when participants perceived the EU to weakly support binding values, but a positive effect when the EU was perceived to strongly support binding values. The results suggest that value alignment plays an important role in perceived legitimacy of the CJEU and EU, and that better representing binding values might be a strategy to improve perceived EU legitimacy. (shrink)

Stuart Russell defines the value alignment problem as follows: How can we build autonomous systems with values that “are aligned with those of the human race”? In this article I outline some distinctions that are useful for understanding the value alignment problem and then propose a solution: I argue that the methods currently applied by computer scientists for embedding moral values in autonomous systems can be improved by representing moral principles as conceptual spaces, i.e. as Voronoi (...) tessellations of morally similar choice situations located in a multidimensional geometric space. The advantage of my preferred geometric approach is that it can be implemented without specifying any utility function ex ante. (shrink)

Value alignment is essential for ensuring that AI systems act in ways that are consistent with human values. Existing approaches, such as reinforcement learning with human feedback and constitutional AI, however, exhibit power asymmetries and lack transparency. These “authoritarian” approaches fail to adequately accommodate a broad array of human opinions, raising concerns about whose values are being prioritized. In response, we introduce the Dynamic Value Alignment approach, theoretically grounded in the principles of parallel constraint satisfaction, which (...) models moral reasoning as a dynamic process that balances multiple value principles. Our approach also enhances users’ moral and epistemic agency by granting users greater control over the values that influence AI behavior. As a more user-centric, transparent, and participatory framework for AI ethics, our approach not only addresses the democratic deficits inherent in current practices but also ensures that AI systems are flexibly aligned with a diverse array of human values. (shrink)

This paper considers challenges resulting from the use of advanced artificial judicial intelligence (AAJI). We argue that these challenges should be considered through the lens of value alignment. Instead of discussing why specific goals and values, such as fairness and nondiscrimination, ought to be implemented, we consider the question of how AAJI can be aligned with goals and values more generally, in order to be reliably integrated into legal and judicial systems. This value alignment framing draws (...) on AI safety and alignment literature to introduce two otherwise neglected considerations for AAJI safety: specification and assurance. We outline diverse research directions and suggest the adoption of assurance and specification mechanisms as the use of AI in the judiciary progresses. While we focus on specification and assurance to illustrate the value of the AI safety and alignment literature, we encourage researchers in law and philosophy to consider what other lessons may be drawn. (shrink)

Abstract: One approach to alignment with human values in AI and robotics is to engineer artiTicial systems isomorphic with human beings. The idea is that robots so designed may autonomously align with human values through similar developmental processes, to realize project ideal conditions through iterative interaction with social and object environments just as humans do, such as are expressed in narratives and life stories. One persistent problem with human value orientation is that different human beings champion different values (...) as ideal, meaning that the values to which an AI should be aligned are ambiguous. Prior work considered human development of purpose and source of meaning in life in terms of project ideal conditions, in effect establishing lifelong value orientations according to which intermediate situations are evaluated. The present work compares views on motivating values from St. Augustine and from popular cognitive science. These accounts are described as divergent error theories which present to their proponents as mutually exclusive yet accurate accounts of personal experience due to differential development of variable innate potentials. SpeciTically, the hypothesis proposed is that differential development of spindle neural projections establishes enduring connections between prior established relatively immediate routine processes entrained during childhood and prioritized in popular cognitive science, and later developing higher-level social and self-processes entrained during adolescence and emphasized in Augustine's account, with these projections hard-wiring lifelong motivating value orientations more or less inaccessible to modiTication through material interaction. Robot experiments informed by this study may evaluate variable value orientation by design, with for example autonomous robots developing motivating associations with temporally distal project ideal conditions through love for humanity, as described by Augustine, and others pursuing adaptive Tit to passing norms consistent with popular contemporary accounts. (shrink)

The “Value Alignment Problem” is the challenge of how to align the values of artificial intelligence with human values, whatever they may be, such that AI does not pose a risk to the existence of humans. Existing approaches appear to conceive of the problem as "how do we ensure that AI solves the problem in the right way", in order to avoid the possibility of AI turning humans into paperclips in order to “make more paperclips” or eradicating the (...) human race to “solve climate change”. This paper proposes an approach to Alignment rooted in the Enactive theory of mind that reconceptualises it as "how do we make relevant to AI what it relevant to humans". This conceptualisation is supported with a discussion of 4E cognition and goes on to suggest that the Alignment problem and the Frame problem are the same problem. The paper concludes with a discussion of the tradeoffs of the different approaches to value alignment. (shrink)

Human beings are internally inconsistent in various ways. One way to develop this thought involves using the language of value alignment: the values we hold are not always aligned with our behavior, and are not always aligned with each other. Because of this self-misalignment, there is room for potential projects of human enhancement that involve achieving a greater degree of value alignment than we presently have. Relatedly, discussions of AI ethics sometimes focus on what is known (...) as the value alignment problem, the challenge of how to build AI that acts in accordance with our human values. We argue that there is an especially close connection between solving the value alignment problem in AI ethics and using AI to pursue certain forms of human enhancement. But in addition, we also argue that there are important limits to what kinds of human enhancement can be pursued in this way, because some forms of human enhancement—namely moral revolutions—involve a kind of value misalignment rather than alignment. (shrink)

We outline a four-step process for ML/AI developers to align development choices with multiple values, by adapting a widely-utilized framework from bioethics: (1) identify the values that matter, (2) specify identified values, (3) find solution spaces that allow for maximal alignment with identified values, and 4) make hard choices if there are unresolvable trade-offs between the identified values. Key to this approach is identifying resolvable trade-offs between values (Step 3). We survey ML/AI methods that could be used to this (...) end, identifying approaches at each stage of the development process. All steps should be guided by community engagement. The framework outlines what it means to build a value-aligned ML/AI system, providing development teams with practical guidance to maximize the chances their work has desirable impacts. (shrink)

The value alignment problem for artificial intelligence (AI) asks how we can ensure that the “values”—i.e., objective functions—of artificial systems are aligned with the values of humanity. In this paper, I argue that linguistic communication is a necessary condition for robust value alignment. I discuss the consequences that the truth of this claim would have for research programmes that attempt to ensure value alignment for AI systems—or, more loftily, those programmes that seek to design (...) robustly beneficial or ethical artificial agents. (shrink)

AI research is being challenged with ensuring that autonomous agents learn to behave ethically, namely in alignment with moral values. Here, we propose a novel way of tackling the value alignment problem as a two-step process. The first step consists on formalising moral values and value aligned behaviour based on philosophical foundations. Our formalisation is compatible with the framework of (Multi-Objective) Reinforcement Learning, to ease the handling of an agent’s individual and ethical objectives. The second step (...) consists in designing an environment wherein an agent learns to behave ethically while pursuing its individual objective. We leverage on our theoretical results to introduce an algorithm that automates our two-step approach. In the cases where value-aligned behaviour is possible, our algorithm produces a learning environment for the agent wherein it will learn a value-aligned behaviour. (shrink)

Norms have been widely enacted in human and agent societies to regulate individuals’ actions. However, although legislators may have ethics in mind when establishing norms, moral values are only sometimes explicitly considered. This paper advances the state of the art by providing a method for selecting the norms to enact within a society that best aligns with the moral values of such a society. Our approach to aligning norms and values is grounded in the ethics literature. Specifically, from the literature’s (...) study of the relations between norms, actions, and values, we formally define how actions and values relate through the so-called value judgment function and how norms and values relate through the so-called norm promotion function. We show that both functions provide the means to compute value alignment for a set of norms. Moreover, we detail how to cast our decision-making problem as an optimisation problem: finding the norms that maximise value alignment. We also show how to solve our problem using off-the-shelf optimisation tools. Finally, we illustrate our approach with a specific case study on the European Value Study. (shrink)

Evidence suggests that the incidence of research misconduct is not in decline despite efforts to improve awareness, education and governance mechanisms. Two responses to this problem are favoured: first, the promotion of an agent-centred ethics approach to enhance researchers’ personal responsibility and accountability, and second, a change in research culture to relieve perceived pressures to engage in misconduct. This article discusses the challenges for both responses and explains how normative coherence through values alignment might assist. We argue that research (...) integrity and research ethics convey mixed messages, which are likely to contribute to a form of normative confusion. For the successful adoption of an agent-centred approach, normative coherence is needed between the two. To facilitate normative coherence, we propose that research ethics and research integrity be underpinned by a shared set of moral values that can be enacted via codes and guidelines and imbue research environments. Furthermore, to facilitate culture change, the same normative coherence is necessary at all levels of an institution. Only via values alignment between institutional aims, management, institutional practices and researchers can an ethical culture become truly embedded in research institutions. (shrink)

In order to maximize human performance, defence forces continue to explore, develop, and apply human performance enhancement (HPE) methods, ranging from pharmaceuticals to (bio)technological enhancement. This raises ethical, legal, and societal concerns and requires organizing a careful reflection and deliberation process, with relevant stakeholders. We discuss a range of ethical, legal, and societal aspects (ELSA), which people involved in the development and deployment of HPE can use for such reflection and deliberation. A realistic military scenario with proposed HPE application can (...) serve as a starting point for such an iterative and participatory process. Stakeholders can discuss this application, modify its features, and design appropriate processes around it – for instance, procedures for informed consent. We propose that organizing aspects into these three categories – ethical, legal, and societal – can help involve appropriate interlocutors at different moments: legal aspects with people in strategy or management roles, from the start of a project; ethical aspects with people in operations and medical roles, during development; and societal aspects with people in communication and personnel roles, during deployment. Notably, we developed and discussed this framework and the three aspects in close collaboration with personnel from the military. (shrink)

AI research is being challenged with ensuring that autonomous agents learn to behave ethically, namely in alignment with moral values. Here, we propose a novel way of tackling the value alignment problem as a two-step process. The first step consists on formalising moral values and value aligned behaviour based on philosophical foundations. Our formalisation is compatible with the framework of (Multi-Objective) Reinforcement Learning, to ease the handling of an agent’s individual and ethical objectives. The second step (...) consists in designing an environment wherein an agent learns to behave ethically while pursuing its individual objective. We leverage on our theoretical results to introduce an algorithm that automates our two-step approach. In the cases where value-aligned behaviour is possible, our algorithm produces a learning environment for the agent wherein it will learn a value-aligned behaviour. (shrink)

How do we ensure that future generally intelligent AI share our values? This is the value-alignment problem. It is a weighty matter. After all, if AI are neutral with respect to our wellbeing, or worse, actively hostile toward us, then they pose an existential threat to humanity. Some philosophers have argued that one important way in which we can mitigate this threat is to develop only AI that shares our values or that has values that ‘align with’ ours. (...) However, there is nothing to guarantee that this policy will be universally implemented—in particular, ‘bad actors’ are likely to flout it. In this paper, I show how the predictive processing model of the mind, currently ascendant in cognitive science, may ameliorate the value-alignment problem. In essence, I argue that there are a plurality of reasons why any future generally intelligent AI will possess a predictive processing cognitive architecture (e.g. because we decide to build them that way; because it is the only possible cognitive architecture that can underpin general intelligence; because it is the easiest way to create AI.). I also argue that if future generally intelligent AI possess a predictive processing cognitive architecture, then they will come to share our pro-moral motivations (of valuing humanity as an end; avoiding maleficent actions; etc.), regardless of their initial motivation set. Consequently, these AI will pose a minimal threat to humanity. In this way then, I conclude, the value-alignment problem is significantly ameliorated under the assumption that future generally intelligent AI will possess a predictive processing cognitive architecture. (shrink)

RRI is a broad concept that is subject to different interpretations. This chapter focuses on the view of RRI as a transformative ideal for reforming the research and innovation system in the service of public interest. This is the normatively strong view of RRI that has attracted many policy-makers and young researchers but left cold many senior researchers and innovators. The transformative vision of RRI has failed to materialise, and RRI remains a marginal reality, even in Norway, where arguably the (...) conditions were more propitious than elsewhere. I attempt to explain the failed transformation, focusing on two key objectives of RRI: the ambition of aligning R&I with societal values and the aspiration to steer R&I through generating a shared responsibility for the future (a prospective joint responsibility in technical terms). Alignment proved very hard to achieve because valuing is steeped in well-established practices, habits, and cognitive-emotional frameworks. These cannot be changed at will. Besides, the ambition to make researchers and innovators more responsive to a wider constituency and additional social responsibilities stumbled against what I call moral saturation, namely the lack of capacity and resources to take on additional moral tasks. Furthermore, modern societies are characterised by a pluralism of values and conceptions of the good life, compounded by the lack of methods for composing value conflicts. These problems come back when we look at what it takes to create expanded shared responsibilities: joint intentions and joint commitments. A formal analysis of how these can be generated shows that they need pre-conditions that are seldom obtaining in the real world of R&I. So, the transformative ambition went against the inertia and entrenched habits of the R&I ecosystem and yet very often the task of promoting the change was given to junior researchers: the most vulnerable and less powerful actors. I conclude that RRI ambition to transform the R&I system is unrealistic. What can be attempted is to develop small-scale experiments outside the mainstream, where institutional barriers and perverse incentives are partially removed or corrected. (shrink)

Some researchers have recognized that privileged communities dominate the discourse on AI Ethics, and other voices need to be heard. As such, we identify the current ethics milieu as arising from WEIRD (Western, Educated, Industrialized, Rich, Democratic) contexts, and aim to expand the discussion to non-WEIRD global communities, who are also stakeholders in global sociotechnical systems. We argue that accounting for honor, along with its values and related concepts, would better approximate a global ethical perspective. This complex concept already underlies (...) some of the WEIRD discourse on AI ethics, but certain cultural forms of honor also bring overlooked issues and perspectives to light. We first describe honor according to recent empirical and philosophical scholarship. We then review “consensus” principles for AI ethics framed from an honor-based perspective, grounding comparisons and contrasts via example settings such as content moderation, job hiring, and genomics databases. A better appreciation of the marginalized concept of honor could, we hope, lead to more productive AI value alignment discussions, and to AI systems that better reflect the needs and values of users around the globe. (shrink)

This research uses a survey to analyze types of benefits sought by partners in cross-sector collaborations in Spain and to test and build upon theories that indicate prior collaboration experience and partner alignment will positively affect value creation through the collaboration. Using exploratory factor analysis to operationalize a broad range of potential benefits into more specific concepts, the results of this study identify distinct factors that characterize the types of benefits sought by non-profit organizations and businesses engaged in (...) cross-sector collaborations. Findings show that prior experience and alignment positively affect each factor for value creation. Prior experience is also found to influence the type of benefits sought from cross-sector collaborations and to positively affect alignment in terms of mission and strategy. Unexpectedly, the study also finds that prior experience moderates the effect of alignment on value creation. (shrink)

Artificial Intelligence (AI) must be directed at humane ends. The development of AI has produced great uncertainties of ensuring AI alignment with human values (AI value alignment) through AI operations from design to use. For the purposes of addressing this problem, we adopt the phenomenological theories of material values and technological mediation to be that beginning step. In this paper, we first discuss the AI value alignment from the relevant AI studies. Second, we briefly present (...) what are material values and technological mediation and reflect on the AI value alignment through the lenses of these theories. We conclude that a set of finite human values can be defined and adapted to the stable life tasks that AI systems will be called upon to accomplish. The AI value alignment can also be fostered between designers and users through technological mediation. Upon that foundation, we propose a set of common principles to understand the AI value alignment through phenomenological theories. This paper contributes the unique knowledge of phenomenological theories to the discourse on AI alignment with human values. (shrink)

Book review of Carlos Montemayor's "The Prospect of a Humanitarian Artificial Intelligence: Agency and Value Alignment" || Reseña del libro "The Prospect of a Humanitarian Artificial Intelligence: Agency and Value Alignment", escrito por Carlos Montemayor.

This study examines how values and communication in the workplace differ across different generations, with data analyzed from 223 participants using one-way analysis of variance (ANOVA). The research reveals notable differences in individual and organizational values between different generations and evaluates how effectively values are communicated and aligned across various age groups. Some key discoveries include variations in how different age groups view the level of respect towards personal values within an organization (H5, f = 3.632, p = 0.015) and (...) the recognition of individual values (H8, f = 2.912, p = 0.038). However, the theories regarding the importance of organizational values (H1), smooth intergenerational communication (H3), and the influence of aligning values on job satisfaction (H10) were not supported. The research highlights the significance of recognizing and dealing with differences in values among different generations in order to improve communication and unity within organizations. (shrink)

Roughly, empirical AI alignment research (AIA) is an area of AI research which investigates empirically how to design AI systems in line with human goals. This paper examines the role of non-epistemic values in AIA. It argues that: (1) Sciences differ in the degree to which values influence them. (2) AIA is strongly value-laden. (3) This influence of values is managed inappropriately and thus threatens AIA’s epistemic integrity and ethical beneficence. (4) AIA should strive to achieve value (...) transparency, critical scrutiny from inside and outside the discipline – involving the public –, and to empower actors without strong commercial interests. (shrink)

This book argues that politics must align with the promotion of self-actualization. Combining private property rights with an ethics of responsibility and drawing from the ideas of Immanuel Kant, the book opens the doors to a nonpartisan analysis of income inequality, inheritance, race relations, abortion and governance.

The threat from possible future superintelligent AI has given rise to discussion of the so-called “value alignment problem”. This is the problem of how to ensure artificially intelligent systems align with human values, and thus (hopefully) mitigate risks associated with them. Naturally, AI value alignment is often discussed in relation to morally relevant values, such as the value of human lives or human wellbeing. However, solutions to the value alignment problem target all human (...) values, not only morally relevant ones. Is there a value alignment problem in other domains? In this paper, I explore whether the AI value alignment problem extends beyond morally relevant values to include aesthetic values. I demonstrate that the value alignment problem as typically framed includes aesthetic values, and, using examples from computer vision, put forward that AI may be misaligned with human values in the artistic realm. Whilst misalignment may be cause for concern when considering AI creativity, I argue that aesthetic value is a case in which we do not want AI to be fully aligned with human values. In doing so, I offer support to Peterson’s moderate value alignment thesis. (shrink)

As artificial intelligence systems are becoming increasingly autonomous and will soon be able to make decisions on their own about what to do, AI researchers have started to talk about the need to align AI with human values. The AI ‘value alignment problem’ faces two kinds of challenges—a technical and a normative one—which are interrelated. The technical challenge deals with the question of how to encode human values in artificial intelligence. The normative challenge is associated with two questions: (...) “Which values or whose values should artificial intelligence align with?” My concern is that AI developers underestimate the difficulty of answering the normative question. They hope that we can easily identify the purposes we really desire and that they can focus on the design of those objectives. But how are we to decide which objectives or values to induce in AI, given that there is a plurality of values and moral principles and that our everyday life is full of moral disagreements? In my paper I will show that although it is not realistic to reach an agreement on what we, humans, really want as people value different things and seek different ends, it may be possible to agree on what we do not want to happen, considering the possibility that intelligence, equal to our own, or even exceeding it, can be created. I will argue for pluralism which is compatible with objectivism. In spite of the fact that there is no uniquely best solution to every moral problem, it is still possible to identify which answers are wrong. And this is where we should begin the value alignment of AI. (shrink)

There is a growing consensus among philosophers that quantifying value-laden concepts can be epistemically successful and politically legitimate if all value-laden choices in the process of quantification are aligned with stakeholder values. I argue that proponents of this view have failed to argue for its basic premise: successful quantification is sufficiently unconstrained so that it can be achieved along multiple stakeholder-specific pathways. I then challenge this premise by considering a rare example of successful value-laden quantification in seismology. (...) Seismologists quantified earthquake size precisely by excluding stakeholder values from measure design and testing. (shrink)

This paper looks at philosophical questions that arise in the context of AI alignment. It defends three propositions. First, normative and technical aspects of the AI alignment problem are interrelated, creating space for productive engagement between people working in both domains. Second, it is important to be clear about the goal of alignment. There are significant differences between AI that aligns with instructions, intentions, revealed preferences, ideal preferences, interests and values. A principle-based approach to AI alignment, (...) which combines these elements in a systematic way, has considerable advantages in this context. Third, the central challenge for theorists is not to identify ‘true’ moral principles for AI; rather, it is to identify fair principles for alignment that receive reflective endorsement despite widespread variation in people’s moral beliefs. The final part of the paper explores three ways in which fair principles for AI alignment could potentially be identified. (shrink)

Historically, scientific and engineering expertise has been key in shaping research and innovation policies, with benefits presumed to accrue to society more broadly over time. But there is persistent and growing concern about whether and how ethical and societal values are integrated into R&I policies and governance, as we confront public disbelief in science and political suspicion toward evidence-based policy-making. Erosion of such a social contract with science limits the ability of democratic societies to deal with challenges presented by new, (...) disruptive technologies, such as synthetic biology, nanotechnology, genetic engineering, automation and robotics, and artificial intelligence. Many policy efforts have emerged in response to such concerns, one prominent example being Europe's Eighth Framework Programme, Horizon 2020, whose focus on “Responsible Research and Innovation” provides a case study for the translation of such normative perspectives into concrete policy action and implementation. Our analysis of this H2020 RRI approach suggests a lack of consistent integration of elements such as ethics, open access, open innovation, and public engagement. On the basis of our evaluation, we suggest possible pathways for strengthening efforts to deliver R&I policies that deepen mutually beneficial science and society relationships. (shrink)

Social projects are based on ethical values that members defend, incorporate in their life and want to implement. Identity and mission play an important role in the transmission of values within or...

Continuing Education (CE) aims to help health professionals fulfill their ethical responsibility of maintaining professional competence. This research compares the CE guidelines and standards of 11 health professional organizations in relation to five domains of evolving professional values: ethics, cultural diversity, social justice, interprofessionalism, and self-care. Results showed that ethics received the greatest attention across the CE standards, followed by interprofessionalism and cultural diversity. This study offers a starting point for CE accreditors to examine the extent to which their CE (...) standards align with their profession’s stipulated values, and to situate themselves within the broader context of health profession accreditors. (shrink)

This paper highlights the emergence of different ‘vocabularies’ that describe various values-driven business functions within large organizations and argues for improved horizontal alignment between them. We investigate two established functions that have long-standing organizational histories: Ethics and Compliance and Corporate Social Responsibility. By drawing upon research on organizational alignment, we explain both the need for and the potential benefit of greater alignment between these values-driven functions. We then examine the structural and socio-cultural dimensions of organizational systems through (...) which E&C and CSR horizontal alignment can be coordinated to improve synergies, address tensions, and generate insight to inform future research and practice in the field of Business and Society. The paper concludes with research questions that can inform future scholarly research and a practical model to guide organizations’ efforts towards inter-functional, horizontal alignment of values-driven organizational practice. (shrink)

We argue that two long-term goals of AI research stand in tension with one another. The first involves creating AI that is safe, where this is understood as solving the problem of value alignment. The second involves creating artificial general intelligence, meaning AI that operates at or beyond human capacity across all or many intellectual domains. Our argument focuses on the human capacity to make what we call “existential choices”, choices that transform who we are as persons, including (...) transforming what we most deeply value or desire. It is a capacity for a kind of value misalignment, in that the values held prior to making such choices can be significantly different from (misaligned with) the values held after making them. Because of the connection to existentialist philosophers who highlight these choices, we call the resulting form of risk “existentialist risk.” It is, roughly, the risk that results from AI taking an active role in authoring its own values rather than passively going along with the values given to it. On our view, human-like intelligence requires a human-like capacity for value misalignment, which is in tension with the possibility of guaranteeing value alignment between AI and humans. (shrink)

Large-scale language technologies are increasingly used in various forms of communication with humans across different contexts. One particular use case for these technologies is conversational agents, which output natural language text in response to prompts and queries. This mode of engagement raises a number of social and ethical questions. For example, what does it mean to align conversational agents with human norms or values? Which norms or values should they be aligned with? And how can this be accomplished? In this (...) paper, we propose a number of steps that help answer these questions. We start by developing a philosophical analysis of the building blocks of linguistic communication between conversational agents and human interlocutors. We then use this analysis to identify and formulate ideal norms of conversation that can govern successful linguistic communication between humans and conversational agents. Furthermore, we explore how these norms can be used to align conversational agents with human values across a range of different discursive domains. We conclude by discussing the practical implications of our proposal for the design of conversational agents that are aligned with these norms and values. (shrink)

Abstract:The mission and value statements of healthcare organizations serve as the foundational philosophy that informs all aspects of the organization. The ultimate goal is seamless alignment of values to mission in a way that colors the overall life and culture of the organization. However, full alignment between healthcare organizational values and mission in a fashion that influences the daily life and culture of healthcare organizations does not always occur. Grounded in the belief that a lack of organizational (...) alignment to explicit organizational mission and value statements often stems from the failure to develop processes that enable realization of the leadership’s good intentions, the authors propose an organizational ethics dashboard to empower leaders of healthcare organizations to assess the adequacy of systems in place to support alignment with the stated ethical mission. (shrink)

The paper proposes a way to naturalise Charles S. Peirce’s conception of the scientific method, which he specified in terms of abduction, deduction and induction. The focus is on the central issue of the economy of research in abduction and self-correction by error reduction in induction. We show how Peirce’s logic of science receives support from modern breakthroughs in computational neuroscience, and more specifically from Karl Friston’s statements of active inference and the Free Energy Principle, namely the account of how (...) organisms’ capacity to decrease the discrepancy between the expected value and actual outcomes entails the minimisation of errors in their hypotheses about the world. A scientific account of organisms’ capacity to choose policies and form expectations is aligned with Peirce’s theories of abduction and induction, and especially with the economy of research. The upshot is the recovery of Peirce’s theory of the logic of science in the context of active inquiry. (shrink)

As artificial intelligence (AI) continues to advance, one key challenge is ensuring that AI aligns with certain values. However, in the current diverse and democratic society, reaching a normative consensus is complex. This paper delves into the methodological aspect of how AI ethicists can effectively determine which values AI should uphold. After reviewing the most influential methodologies, we detail an intuitionist research agenda that offers guidelines for aligning AI applications with a limited set of reliable moral intuitions, each underlying a (...) refined cooperative view of AI. We discuss appropriate epistemic tools for collecting, filtering, and justifying moral intuitions with the aim of reducing cognitive and social biases. The proposed methodology facilitates a large collective participation in AI alignment, while ensuring the reliability of the considered moral judgments. (shrink)

Values‐based practice is deemed essential for healthcare provision worldwide. In England, values‐based recruitment methods, such as multiple mini interviews (MMIs), are employed to ensure that healthcare students’ personal values align with the values of the National Health Service (NHS), which focus on compassion and patient‐centeredness. However, values cannot be seen as static constructs. They can be positively and negatively influenced by learning and socialisation. We have conceptualised students’ perceptions of their values over the duration of their education programme as a (...) ‘values journey’. The aim of this hermeneutic longitudinal focus group study was to explore the ‘values journey’ of student nurses and midwives, recruited through MMIs, across the 3 years of their education programme. The study commenced in 2016, with 42 nursing and midwifery students, originally recruited onto their programmes through multiple mini interviews. At the third and final point of data collection, 25 participants remained. Findings indicate that students' confidence, courage and sense of accountability increased over the 3 years. However, their values were also shaped by time constraints, emotional experiences and racial discrimination. We argue that adequate psychological support is necessary as healthcare students embark on and progress through their values journey, and propose a framework for this. (shrink)

The paper demonstrates that social alignment is distinct from value alignment as it is currently understood in the AI safety literature, and argues that social alignment is an important research agenda. Work provides an important example for the argument, since work is a cooperative endeavor, and it is part of the larger manifold of social cooperation. These cooperative aspects of work are individually and socially valuable, and so they must be given a central place when evaluating (...) the impact of AI upon work. Workplace technologies are not simply instruments for achieving productive goals, but ways of mediating interpersonal relations. They are aspects of a cooperative interface i.e. the infrastructure by which we engage cooperative behavior with others. The concept of the cooperative interface suggests two conjectures to foreground in the social alignment agenda, motivated by the experience of algorithmic trading and social robotics: that AI impacts cooperation through its effects on social networks, and through its effects on social norms. (shrink)

This paper uses famous problems from philosophy of science and philosophical psychology—underdetermination of theory by evidence, Nelson Goodman’s new riddle of induction, theory-ladenness of observation, and “Kripkenstein’s” rule-following paradox—to show that it is empirically impossible to reliably interpret which functions a large language model (LLM) AI has learned, and thus, that reliably aligning LLM behavior with human values is provably impossible. Sections 2 and 3 show that because of how complex LLMs are, researchers must interpret their learned functions largely in (...) terms of empirical observations of their outputs and network behavior. Sections 4–7 then show that for every “aligned” function that might appear to be confirmed by empirical observation, there is always an infinitely larger number of “misaligned”, arbitrarily time-limited functions equally consistent with the same data. Section 8 shows that, from an empirical perspective, we can thus never reliably infer that an LLM or subcomponent of one has learned any particular function at all before any of an uncountably large number of unpredictable future conditions obtain. Finally, Section 9 concludes that the probability of LLM “misalignment” is—at every point in time, given any arbitrarily large body of empirical evidence—always vastly greater than the probability of “alignment.”. (shrink)

New technologies not only contribute greatly to society and the economy; they also involve fundamental societal shifts, challenging our values and ideas about ourselves and the world. With a view to aligning technological change and innovation with ethical values, the concept of responsible innovation advocates the inclusion of a variety of stakeholders, in particular from society. In shifting moral responsibility towards the producers of innovations, responsible innovation rejects the standard normative economic view that the ethical evaluation of innovations is a (...) matter of individual consumers’ market-based choices. However, in this article we argue that responsible innovation should not abandon all normative consideration of the individual outright, to which end we present an alternative normative economic approach based on preference learning. We show how this approach can provide an enhanced understanding of responsible innovation by clarifying the redistribution of moral responsibility and casting individuals in the normative role of co-innovators, rather than mere consumers. We argue that responsible innovation should enable individuals to form preferences and evaluate innovations, so as to align innovation with ethical demands. Finally, we show how our proposed approach can be put into practice in so-called laboratories in real-world contexts, using methods from the field of design. In short, drawing on normative economics, this article aims to establish a new understanding of responsible innovation that is conceptually sound and can form the basis for novel innovation practices. (shrink)

Prior research flags the inherent incompatibilities between for-profit and nonprofit partners and cautions that clashing value creation logics and conflicting identities can stall social innovation in cross sector partnerships. Process narratives of successful versus unsuccessful cross sector partnerships paint a more optimistic picture, whereby the frequency, intensity, breadth, and depth of interactions may afford frame alignment despite partners' divergent value creation approaches. However, little is known about how cross sector partners come to recognize and reconcile their divergent (...) value creation frames in order to co-construct social value. Using longitudinal narratives of four dyads, we show that partners initially contrast their sector-embedded diagnostic frames and then work together to deliberately develop partnership-specific prognostic frames. We extend the literature on framing by developing a four-stage grounded model of frame negotiation, elasticity, plasticity, and fusion which unpacks the relational process of value creation in cross sector partnerships. Our qualitative analyses further show how partners orchestrate multilevel coordination that helps scaffold and calibrate this relational process of frame fusion. (shrink)

In alignment with stated social, health, and environmental values, hundreds of hospitals in the United States are purchasing local, organic, and other alternative foods. Due to the logistical and economic constraints associated with feeding hundreds to thousands of people every day, new food procurement initiatives in hospitals grapple with integrating conventional supply chain norms of efficiency, standardization, and affordability while meeting the diverse values driving them such as mutual benefit between supply chain members, environmental stewardship, and social equity. This (...) paper provides empirical data and analysis on emerging values-based supply chains in hospitals that attempt to meet both the scale-based requirements and values-based goals of alternative food procurement initiatives. In particular, it examines tensions among industrial, economic, and alternative agrifood values in relation to a particular set of hospital supply chain players called Group Purchasing Organizations. Hospital membership in GPOs in the United States is ubiquitous, and 80–90 % of a hospital’s foodservice procurement comes through GPO channels in keeping with contract terms. GPO-governed supply chains are deeply rooted in industrial and commercial norms, in other words, price competition, economic efficiency, and forces of standardization through adherence to technical and quality standards. The bulk of alternative food procurement initiatives in the health care sector currently occur outside of the GPO–hospital relationship, however, over 90 % of hospital foodservice directors interviewed for this research expressed a desire to increase sustainable food procurement through their GPO. This study finds that, if alternative agrifood efforts in the health care sector are to integrate with GPO-governed supply chains without losing the robustness of the original values and goals that brought them into being, concerns related to supply chain structure, transparency and traceability of alternative food attributes, and alignment of definitions of local and sustainable food between all supply chain members will need to be addressed. This study also details points of flexibility in health care food supply chains and the potential for hospitals to create purchasing and informational alliances around common food goals in order to create new, values-based supply chain relationships both within and beyond GPO procurement channels. (shrink)

The Economy for the Common Good proposes a more ethical and sustainable society and organizations based on the common good concept. The study investigates entrepreneurs' reasons for joining the ECG movement and organizational changes introduced following the implementation of the ECG managerial system. Semistructured interviews were held with managers of nine Italian organizations belonging to the movement. Interviews were transcribed, and qualitative content analysis was performed using NVivo 12. Eleven nodes integrating 279 answer units were coded, addressing reasons for adhering, (...) actions introduced, difficulties, overcoming strategies and enablers. The results suggest that ECG values and particularly Environmental Sustainability and Human Dignity are two main reasons to join the movement, that a Common Good Report is a valuable tool for the organizational analysis, that such analysis can be replicated with other ECG organizations, and that pursuing decent work conditions strengthens the adhesion to the ECG movement. The seven conceptual propositions highlight the congruence between the value structure of the organization and the values of the ECG, the congruence between the values held by proximal organizational stakeholders and the changes encouraged by ECG approach, and that rewards and recognition by the organizational stakeholders and society reinforce and maintain the adhesion path. (shrink)

Harmonic Alignment was proposed by Prince and Smolensky (1993) as a mechanism to establish a correspondence between different harmony scales within the overall framework of Optimality Theory (“OT” henceforth). They specifically address the combination of the phonological sonority hierarchy with the hierarchy of syllable positions. In recent work, Judith Aissen has taken up this idea as a mean to formulate insights from the functionally oriented markedness theory in morphology and syntax within OT syntax (cf. Aissen 1999, 2000). Though based (...) on earlier work in typology like Silverstein (1981) , Aissen manages a formalization of a mechanism that promises an account of much that seems quaint and bizarre about natural languages when considered from the perspective of e.g. a designer of computer languages or logical formalisms. Suppose a linguistic item can be classified according to two features, A and B. Suppose furthermore that A has two possible values, A1 and A2, while B has n possible values, B1 . . . Bn, for some n ≥ 2. Finally, the values of each both features are ranked according to their prominence. Lets say that A1 is more prominent than A2, and Bi is more prominent than Bj iff i < j. Formally, we thus have the prominence scales.. (shrink)

Inchul Yum (2024) argues that the widespread adoption of language agent architectures would likely increase the risk posed by AI by simplifying the process of aligning artificial systems with human values and thereby making it easier for malicious actors to use them to cause a variety of harms. Yum takes this to be an example of a broader phenomenon: progress on the alignment problem is likely to be net safety-negative because it makes artificial systems easier for malicious actors to (...) control. I offer some reasons for skepticism about this surprising and pessimistic conclusion. (shrink)

New technologies such as smart sensors improve rehabilitation processes and thereby increase older adults’ capabilities to participate in social life, leading to direct physical and mental health benefits. Wearable smart sensors for home use have the additional advantage of monitoring day-to-day activities and thereby identifying rehabilitation progress and needs. However, identifying and selecting rehabilitation priorities is ethically challenging because physicians, therapists, and caregivers may impose their own personal values leading to paternalism. Therefore, we develop a discussion template consisting of a (...) series of adaptable questions for the patient–physician encounter based on the capability approach. The goal is to improve geriatric rehabilitation and thereby increase participation in social life and well-being. To achieve this goal, we first analyzed what is considered important for participation on basis of the capability approach, human rights, and ethics of care. Second, we conducted an ethical analysis of each of the four identified dimensions of participation: political, economic, socio-cultural, and care. To improve compliance with rehabilitation measures, health professionals must align rehabilitation measures in an open dialogue with the patient’s aspiration for participation in each dimension. A discussion template based on the capability approach allows for a proactive approach in patient information and stimulates a critical assessment of treatment alternatives while reducing the risk of imposing personal values. (shrink)