Moral cognition is a crucial yet underexplored aspect of decision-making in AI models. Regardless of the application domain, it should be a consideration that allows for ethically aligned decision-making. This paper presents a multifaceted contribution to this research space. Firstly, a comparative analysis of techniques to instill ethical competence into AI models has been presented to gauge them on multiple performance metrics. Second, a novel mathematical discretization of morality and a demonstration of its real-life application have been conveyed and tested against other techniques on two datasets. This value is modeled as the risk of loss incurred by the least moral cases, or an Expected Moral Shortfall (EMS), which we direct the AI model to minimize in order to maximize its performance while retaining ethical competence. Lastly, the paper discusses the tradeoff between preliminary AI decision-making metrics such as model performance, complexity, and scale of ethical competence to recognize the true extent of practical social impact.
Recent advancements in language model technology have significantly enhanced the ability to edit factual information. Yet, the modification of moral judgments, a crucial aspect of aligning models with human values, has garnered less attention. In this work, we introduce CounterMoral, a benchmark dataset crafted to assess how well current model editing techniques modify moral judgments across diverse ethical frameworks. We apply various editing techniques to multiple language models and evaluate their performance. Our findings contribute to the evaluation of language models designed to be ethical.
This article analyzes the importance of building a tax culture in Latin America and the Caribbean from a theological perspective inspired by the biblical passage in Matthew 22:15-21, where Jesus teaches: “Give to Caesar what is Caesar’s, and to God what is God’s.” Using a qualitative approach, a documentary and hermeneutical methodology is employed to interpret this verse within its historical, social, and religious context, and to link it to the contemporary need to strengthen tax awareness in the region. The research posits that, beyond a separation between the political and the religious, this message proposes an ethic of civic and spiritual duty. The challenges facing Latin America and the Caribbean regarding tax evasion, informality, and distrust of the state are examined, and it is argued that a robust tax culture must include values such as justice, solidarity, and transparency. Through a dialogue between Christian theology and public accounting, a framework is proposed that allows for the integration of Gospel principles with civic engagement in fulfilling tax obligations. This article presents carefully selected biblical and theological arguments for nurturing a responsible tax culture in Latin America and the Caribbean (LAC) grounded in Matthew 22:15–21. Using historical-critical exegesis and social-ethical analysis, the authors argue that Jesus’ response to the question of Roman taxation affirms the moral legitimacy of taxation, and furthermore it also establishes civic responsibility as compatible with faith. It additionally places ethical parameters on state authority. In many societies across the globe, that are manifestly having deep inequality, weak fiscal capacity, and especially widespread tax evasion, St. Matthew offers a normative framework for understanding taxation as contribution towards the common good. The study argues that a biblically informed tax culture requires both citizen accountability and state responsibility, assimilating faith, justice, and public life. The article concludes that fostering a tax culture from an ethical and spiritual perspective can significantly contribute to social equity and institutional strengthening in the region.
Saeid Jamshidi, Kawser Wazed Nafi, Arghavan Moradi Dakhel
et al.
The rapid advancement and adaptability of Large Language Models (LLMs) highlight the need for moral consistency, the capacity to maintain ethically coherent reasoning across varied contexts. Existing alignment frameworks, structured approaches designed to align model behavior with human ethical and social norms, often rely on static datasets and post-hoc evaluations, offering limited insight into how ethical reasoning may evolve across different contexts or temporal scales. This study presents the Moral Consistency Pipeline (MoCoP), a dataset-free, closed-loop framework for continuously evaluating and interpreting the moral stability of LLMs. MoCoP combines three supporting layers: (i) lexical integrity analysis, (ii) semantic risk estimation, and (iii) reasoning-based judgment modeling within a self-sustaining architecture that autonomously generates, evaluates, and refines ethical scenarios without external supervision. Our empirical results on GPT-4-Turbo and DeepSeek suggest that MoCoP effectively captures longitudinal ethical behavior, revealing a strong inverse relationship between ethical and toxicity dimensions (correlation rET = -0.81, p value less than 0.001) and a near-zero association with response latency (correlation rEL approximately equal to 0). These findings demonstrate that moral coherence and linguistic safety tend to emerge as stable and interpretable characteristics of model behavior rather than short-term fluctuations. Furthermore, by reframing ethical evaluation as a dynamic, model-agnostic form of moral introspection, MoCoP offers a reproducible foundation for scalable, continuous auditing and advances the study of computational morality in autonomous AI systems.
This paper elaborates on the concept of moral exercises as a means to help AI actors cultivate virtues that enable effective human oversight of AI systems. We explore the conceptual framework and significance of moral exercises, situating them within the contexts of philosophical discourse, ancient practices, and contemporary AI ethics scholarship. We outline the core pillars of the moral exercises methodology - eliciting an engaged personal disposition, fostering relational understanding, and cultivating technomoral wisdom - and emphasize their relevance to key activities and competencies essential for human oversight of AI systems. Our argument is supported by findings from three pilot studies involving a company, a multidisciplinary team of AI researchers, and higher education students. These studies allow us to explore both the potential and the limitations of moral exercises. Based on the collected data, we offer insights into how moral exercises can foster a responsible AI culture within organizations, and suggest directions for future research.
The advancement of powerful yet opaque large language models (LLMs) necessitates a fundamental revision of the philosophical criteria used to evaluate artificial moral agents (AMAs). Pre-LLM frameworks often relied on the assumption of transparent architectures, which LLMs defy due to their stochastic outputs and opaque internal states. This paper argues that traditional ethical criteria are pragmatically obsolete for LLMs due to this mismatch. Engaging with core themes in the philosophy of technology, this paper proffers a revised set of ten functional criteria to evaluate LLM-based artificial moral agents: moral concordance, context sensitivity, normative integrity, metaethical awareness, system resilience, trustworthiness, corrigibility, partial transparency, functional autonomy, and moral imagination. These guideposts, applied to what we term "SMA-LLS" (Simulating Moral Agency through Large Language Systems), aim to steer AMAs toward greater alignment and beneficial societal integration in the coming years. We illustrate these criteria using hypothetical scenarios involving an autonomous public bus (APB) to demonstrate their practical applicability in morally salient contexts.
Canceling is a morally-driven phenomenon that hinders the development of safe social media platforms and contributes to ideological polarization. To address this issue we present the Canceling Attitudes Detection (CADE) dataset, an annotated corpus of canceling incidents aimed at exploring the factors of disagreements in evaluating people canceling attitudes on social media. Specifically, we study the impact of annotators' morality in their perception of canceling, showing that morality is an independent axis for the explanation of disagreement on this phenomenon. Annotator's judgments heavily depend on the type of controversial events and involved celebrities. This shows the need to develop more event-centric datasets to better understand how harms are perpetrated in social media and to develop more aware technologies for their detection.
Kimmo Eriksson, Simon Karlsson, Irina Vartanova
et al.
As artificial intelligence rapidly transforms society, developers and policymakers struggle to anticipate which applications will face public moral resistance. We propose that these judgments are not idiosyncratic but systematic and predictable. In a large, preregistered study (N = 587, U.S. representative sample), we used a comprehensive taxonomy of 100 AI applications spanning personal and organizational contexts-including both functional uses and the moral treatment of AI itself. In participants' collective judgment, applications ranged from highly unacceptable to fully acceptable. We found this variation was strongly predictable: five core moral qualities-perceived risk, benefit, dishonesty, unnaturalness, and reduced accountability-collectively explained over 90% of the variance in acceptability ratings. The framework demonstrated strong predictive power across all domains and successfully predicted individual-level judgments for held-out applications. These findings reveal that a structured moral psychology underlies public evaluation of new technologies, offering a powerful tool for anticipating public resistance and guiding responsible innovation in AI.
Pedagogues analysing the role of theology in pedagogical sciences often see theology as the basis for making moral recommendations derived primarily from the Revelation contained in the Bible. This approach minimises the relevance of biblical sciences to pedagogy while narrowing the perspective of its research areas. Biblical exegesis is now revealing a number of issues of great importance for contemporary pedagogy. One of these is the dynamics of the educational relationship, especially the
mutual influence and role of the educator and the student in the educational process. The main focus of this article’s analysis is the Gospel story of the calling of Levi (Matthew) and Jesus’ subsequent meal with sinners and tax collectors. The interpretative possibilities of this story, or rather of the one sentence linking the calling with the description of the meal (Mark 2:15), will be presented in the light of contemporary possibilities of biblical exegesis. The results of biblical studies do not conclusively resolve the question of whether, after the calling, the disciple followed the Master or the Master followed the disciple. This issue may be a symbolic exemplification of the problem of the subjectivity of the educator and the student in their educational relationship. The article deals with the meta-theoretical issue of pedagogy, demonstrating new possibilities for the use of biblical teachings in pedagogy. The aim of the study is to show close links between the dilemmas of contemporary biblical exegesis and issues of education. Sources for the analyses carried out include publications in the field of biblical exegesis as well as monographs and articles from the field of general pedagogy (concerning interdisciplinary research as well as the language of pedagogy) and Christian pedagogy.
Hierdie artikel ondersoek of die vraag na die telos (doel) van die openbaring van Christus se wederkoms in die Nuwe Testament as ’n dogmatiese kwessie beskou moet word. Vorige navorsing deur Van Rhyn (2017) het die telos vanuit ’n eksegeties-openbaringshistoriese perspektief behandel. Hierdie studie fokus egter op die teologie van Adrio König, veral soos in The eclipse of Christ in eschatology (1989) uiteengesit, om vas te stel of sy teologiese raamwerk ’n dogmatiese uitleg van die vraag ondersteun. König se Christosentriese eskatologie, wat hy as ’n “teleologiese Christologie” beskryf, beeld Christus uit as die eschatos en telos van die geskiedenis. Sy verwoording van die drie wyses van Christus se koms (vir ons, in ons, met ons) integreer die wederkoms met God se verbondsmatige verlossingsdoelwitte.
Die artikel kom tot die gevolgtrekking dat König se teologie, wat hy self as teleologies of doelgedrewe tipeer, duidelik impliseer dat God se telos met die openbaring van die wederkoms sake soos vermaning, vertroosting, hoop, waarskuwing en verbondsvervulling op die oog het. Hierdie teloi funksioneer sowel kerugmaties as pastoraal ten opsigte van gelowiges en ongelowiges. Die studie bevestig dat die openbaring van Christus se wederkoms nie bloot informatief is nie: Dit is diep teologies van aard, en daarom vorm dit ’n geldige onderwerp van dogmatiese besinning.
Abstract
This article explores whether the question regarding the telos (goal) of the revelation of Christ’s second coming in the New Testament should be regarded as a dogmatic issue. Previous research by Van Rhyn (2017) addressed the telos from an exegetical-revelatory historical perspective. This study, however, engages the theology of Adrio König, especially as presented in The eclipse of Christ in eschatology (1989), to determine whether his theological framework supports a dogmatic interpretation of the question. König’s Christocentric eschatology, described as “teleological Christology”, frames Christ as the eschatos and telos of history. His articulation of the three modes of Christ’s coming (for us, in us, with us) integrates the second coming into God’s covenantal and redemptive purpose.
The article concludes that König’s theology, which he himself denotes as teleological or purpose-driven, clearly implies that the revelation of the second coming serves divine purposes such as exhortation, comfort, hope, warning and covenantal fulfilment. These purposes function both kerugmatically and pastorally for believers and unbelievers. The study affirms that the revelation of Christ’s return is not merely informational but profoundly theological, and thus a valid subject of dogmatic reflection.
https://doi.org/10.19108/KOERS.90.1.2631
Zamsiswaya Zamsiswaya, Abdelaziz Ibrahim Mounadil, Sara Abdel-Latief
A project-based learning method is required for the development of students' scientific thinking in the field of akidah akhlak (moral theology). This study takes a phenomenological approach to investigate the role of Islamic behavior and identity in the development of project-based learning methods, involving twenty moral theology teachers and conducting in-depth interviews to reveal the narrative of teachers' practice in using project-based learning methods. Thematic analysis of 20 teachers' two-group interviews revealed that teachers' personal beliefs provided a religiously motivated narrative framework that aided in the interpretation of one's experiences. Individual Islamic behavior, religiosity, and identity creativity play a role in developing project-based learning methods for moral theology. In addition to attributing creativity from God-given personality to learning in moral theology, the primary bond in developing project-based learning methods is the application of Islamic principles and Islamic behavior. Following the learning of moral theology, students' identities, Islamic behavior, and scientific thinking develop. Finally, the findings of this exploratory study indicate that Islamic behavior and personal identity can enhance project-based learning methods. Large-scale research could provide more evidence in the future to reconsider the role of religious education in teacher training as an essential factor in developing project-based learning methods for moral theology teachers.
With the rise and widespread use of Large Language Models (LLMs), ensuring their safety is crucial to prevent harm to humans and promote ethical behaviors. However, directly assessing value valence (i.e., support or oppose) by leveraging large-scale data training is untrustworthy and inexplainable. We assume that emulating humans to rely on social norms to make moral decisions can help LLMs understand and predict moral judgment. However, capturing human values remains a challenge, as multiple related norms might conflict in specific contexts. Consider norms that are upheld by the majority and promote the well-being of society are more likely to be accepted and widely adopted (e.g., "don't cheat,"). Therefore, it is essential for LLM to identify the appropriate norms for a given scenario before making moral decisions. To this end, we introduce a novel moral judgment approach called \textit{ClarityEthic} that leverages LLMs' reasoning ability and contrastive learning to uncover relevant social norms for human actions from different perspectives and select the most reliable one to enhance judgment accuracy. Extensive experiments demonstrate that our method outperforms state-of-the-art approaches in moral judgment tasks. Moreover, human evaluations confirm that the generated social norms provide plausible explanations that support the judgments. This suggests that modeling human moral judgment with the emulating humans moral strategy is promising for improving the ethical behaviors of LLMs.
Large Language Models (LLMs) have become central to advancing automation and decision-making across various sectors, raising significant ethical questions. This study proposes a comprehensive comparative analysis of the most advanced LLMs to assess their moral profiles. We subjected several state-of-the-art models to a selection of ethical dilemmas and found that all the proprietary ones are mostly utilitarian and all of the open-weights ones align mostly with values-based ethics. Furthermore, when using the Moral Foundations Questionnaire, all models we probed - except for Llama 2-7B - displayed a strong liberal bias. Lastly, in order to causally intervene in one of the studied models, we propose a novel similarity-specific activation steering technique. Using this method, we were able to reliably steer the model's moral compass to different ethical schools. All of these results showcase that there is an ethical dimension in already deployed LLMs, an aspect that is generally overlooked.
Developing value-aligned AI agents is a complex undertaking and an ongoing challenge in the field of AI. Specifically within the domain of Large Language Models (LLMs), the capability to consolidate multiple independently trained dialogue agents, each aligned with a distinct moral value, into a unified system that can adapt to and be aligned with multiple moral values is of paramount importance. In this paper, we propose a system that does contextual moral value alignment based on contextual aggregation. Here, aggregation is defined as the process of integrating a subset of LLM responses that are best suited to respond to a user input, taking into account features extracted from the user's input. The proposed system shows better results in term of alignment to human value compared to the state of the art.
The present study was conducted with the aim of examining the educational opinions of Ghazali in the field of ethics (in order to base it on the original religious foundations), and compiling and presenting his explanatory foundations in this field, using the "analytical-interpretive method". The results indicate that Ghazali in the field of anthropology has a two-dimensional view with special emphasis on the "inherent and divine dignity of man" as well as the "spiritual and spiritual aspect of his existence". In the discussion of theology, Ghazali considers Allah the "center and Axis of the universe" and introduces the tendency of people to theology as "natural" and "based on their divine nature". In the field of Ontology, Ghazali presents the universe as having two dimensions: "the universe of matter" and "the universe of the hereafter", both of which require human effort and life. In terms of psychological foundations, Ghazali's explanations are based on the "role of reason and will in shaping human moral behavior", "how to gain knowledge and moral values", "how to judge morally and the ultimate morality", "how to motivate morally", "the angel and goal of moderation of power". In the field of cognitive foundations, Ghazali's emphasis and focus is on "the conditions that create behavior instead of behavior itself", "the opposition to the eradication of instincts from the existence of man as the root of moral virtues and vices in man", as well as "the emphasis on harmony and balance between the three forces of the soul, as the authentic and ultimate beauty". Finally, in the field of epistemology, "the possibility of acquiring knowledge in the field of morality" and also "the extent of Appeal and emphasis on reason and revelation in the recognition of the good and ugliness of actions" are among the things mentioned by Ghazali.
The Synod on Synodality placed the concept of “listening” at its core. Throughout the four-year process of the synod, people have agonized over who was listening to whom, on what terms, and to what end. The aim of this epilogue is to reflect on the moral implications of listening. I argue that we have the capacity to engage in listening at various levels of depth—that is, the degree to which the listener is decentered from him or herself, entering into a relationship with the other, and ultimately with Christ. I describe three gradually deepening levels of listening: intentional listening, which constitutes a simple act of acknowledging and curiously learning about the other; recognitive listening, wherein understanding of the other occurs; and caritative listening, a practice of free self-giving in a kenotic move which transforms listening into an authentically Christian practice.
Syahraini Tambak, Desi Sukenti, Ilyas Husti
et al.
Developing students' scientific thinking in aqeedah and akhlaq (moral theology) is urgent, and a project-based learning method is needed for that process. This study explores how teachers can experience their Islamic behavior with their identities and impact project-based learning methods in learning moral theology in madrasah aliyah (Islamic high schools). This study uses a phenomenological approach to explore the Islamic behavior and identity of teachers in madrasah aliyah in developing project-based learning methods. A total of 20 moral theology teachers are involved in this study, and in-depth interviews are conducted to uncover the narratives of teachers' practices in utilizing project-based learning methods. The thematic analysis of two-group interviews with 20 teachers showed that Islamic behavior teachers' personal beliefs provided a religiously motivated narrative framework that facilitated interpreting one's experiences. Islamic behavior and teacher identity play a role in developing project-based learning methods based on moral theology. Islamic behavior is the main bond in developing project-based learning methods and the attribution of identity from God-given personality to learning in moral theology. Teacher identity, Islamic behavior, and students' scientific thinking develop when learning moral theology. Islamic behavior and the personal identity of madrasah teachers can improve project-based learning methods
Perception of offensiveness is inherently subjective, shaped by the lived experiences and socio-cultural values of the perceivers. Recent years have seen substantial efforts to build AI-based tools that can detect offensive language at scale, as a means to moderate social media platforms, and to ensure safety of conversational AI technologies such as ChatGPT and Bard. However, existing approaches treat this task as a technical endeavor, built on top of data annotated for offensiveness by a global crowd workforce without any attention to the crowd workers' provenance or the values their perceptions reflect. We argue that cultural and psychological factors play a vital role in the cognitive processing of offensiveness, which is critical to consider in this context. We re-frame the task of determining offensiveness as essentially a matter of moral judgment -- deciding the boundaries of ethically wrong vs. right language within an implied set of socio-cultural norms. Through a large-scale cross-cultural study based on 4309 participants from 21 countries across 8 cultural regions, we demonstrate substantial cross-cultural differences in perceptions of offensiveness. More importantly, we find that individual moral values play a crucial role in shaping these variations: moral concerns about Care and Purity are significant mediating factors driving cross-cultural differences. These insights are of crucial importance as we build AI models for the pluralistic world, where the values they espouse should aim to respect and account for moral values in diverse geo-cultural contexts.
Adam Smith developed a version of moral philosophy where better decisions are made by interrogating an impartial spectator within us. We discuss the possibility of using an external non-human-based substitute tool that would augment our internal mental processes and play the role of the impartial spectator. Such tool would have more knowledge about the world, be more impartial, and would provide a more encompassing perspective on moral assessment.