Operationalizing Human Values in the Requirements Engineering Process of Ethics-Aware Autonomous Systems

• URL: http://arxiv.org/abs/2602.09921v1
• Date: Tue, 10 Feb 2026 15:54:25 GMT
• Title: Operationalizing Human Values in the Requirements Engineering Process of Ethics-Aware Autonomous Systems
• Authors: Everaldo Silva Júnior, Lina Marsso, Ricardo Caldas, Marsha Chechik, Genaína Nunes Rodrigues,
• Abstract summary: We propose a requirements engineering approach for ethics-aware autonomous systems.<n>We capture human values as normative goals and align them with functional and adaptation goals.<n>We demonstrate the feasibility of the approach through a medical Body Sensor Network case study.
• Score: 3.535946769391712
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Operationalizing human values alongside functional and adaptation requirements remains challenging due to their ambiguous, pluralistic, and context-dependent nature. Explicit representations are needed to support the elicitation, analysis, and negotiation of value conflicts beyond traditional software engineering abstractions. In this work, we propose a requirements engineering approach for ethics-aware autonomous systems that captures human values as normative goals and aligns them with functional and adaptation goals. These goals are systematically operationalized into Social, Legal, Ethical, Empathetic, and Cultural (SLEEC) requirements, enabling automated well-formedness checking, conflict detection, and early design-time negotiation. We demonstrate the feasibility of the approach through a medical Body Sensor Network case study.

Related papers

• The Runtime Dimension of Ethics in Self-Adaptive Systems [5.0803118668252925]
  Self-adaptive systems operate in close interaction with humans, often sharing the same physical or virtual environments.<n>Current approaches encode ethics as fixed, rule-based constraints or as a single chosen ethical theory embedded at design time.<n>This paper advocates a shift from static ethical rules to runtime ethical reasoning for self-adaptive systems.
  arXiv  Detail & Related papers  (2026-02-19T14:57:30Z)
• Requirements for Aligned, Dynamic Resolution of Conflicts in Operational Constraints [2.752817022620644]
  Deployed, autonomous AI systems must often evaluate multiple plausible courses of action in novel or under-specified contexts.<n>This paper characterizes requirements for agent decision making in these contexts.<n>It also identifies the types of knowledge agents require to make decisions robust to agent goals and aligned with human expectations.
  arXiv  Detail & Related papers  (2025-11-14T04:33:15Z)
• Taxonomy of User Needs and Actions [51.86289485979439]
  The growing ubiquity of conversational AI highlights the need for frameworks that capture users' instrumental goals and the situated, adaptive, and social practices through which they achieve them.<n>To address this gap, we introduce the Taxonomy of User Needs and Actions (TUNA), an empirically grounded framework developed through iterative qualitative analysis of 1193 human-AI conversations.<n> TUNA organizes user actions into a three-level hierarchy encompassing behaviors associated with information seeking, synthesis, procedural guidance, content creation, social interaction, and meta-conversation.
  arXiv  Detail & Related papers  (2025-10-07T17:04:42Z)
• Robot-Gated Interactive Imitation Learning with Adaptive Intervention Mechanism [48.41735416075536]
  Interactive Imitation Learning (IIL) allows agents to acquire desired behaviors through human interventions.<n>We propose the Adaptive Intervention Mechanism (AIM), a novel robot-gated IIL algorithm that learns an adaptive criterion for requesting human demonstrations.
  arXiv  Detail & Related papers  (2025-06-10T18:43:26Z)
• Towards Developing Ethical Reasoners: Integrating Probabilistic Reasoning and Decision-Making for Complex AI Systems [4.854297874710511]
  A computational ethics framework is essential for AI and autonomous systems operating in complex, real-world environments.<n>Existing approaches often lack the adaptability needed to integrate ethical principles into dynamic and ambiguous contexts.<n>We outline the necessary ingredients for building a holistic, meta-level framework that combines intermediate representations, probabilistic reasoning, and knowledge representation.
  arXiv  Detail & Related papers  (2025-02-28T17:25:11Z)
• Constrained Human-AI Cooperation: An Inclusive Embodied Social Intelligence Challenge [47.74313897705183]
  CHAIC is an inclusive embodied social intelligence challenge designed to test social perception and cooperation in embodied agents.<n>In CHAIC, the goal is for an embodied agent equipped with egocentric observations to assist a human who may be operating under physical constraints.
  arXiv  Detail & Related papers  (2024-11-04T04:41:12Z)
• Position: Towards Bidirectional Human-AI Alignment [109.57781720848669]
  We argue that the research community should explicitly define and critically reflect on "alignment" to account for the bidirectional and dynamic relationship between humans and AI.<n>We introduce the Bidirectional Human-AI Alignment framework, which not only incorporates traditional efforts to align AI with human values but also introduces the critical, underexplored dimension of aligning humans with AI.
  arXiv  Detail & Related papers  (2024-06-13T16:03:25Z)
• Normative Requirements Operationalization with Large Language Models [3.456725053685842]
  Normative non-functional requirements specify constraints that a system must observe in order to avoid violations of social, legal, ethical, empathetic, and cultural norms. Recent research has tackled this challenge using a domain-specific language to specify normative requirements. We propose a complementary approach that uses Large Language Models to extract semantic relationships between abstract representations of system capabilities.
  arXiv  Detail & Related papers  (2024-04-18T17:01:34Z)
• Disciplining Deliberation: A Sociotechnical Perspective on Machine Learning Trade-offs [0.0]
  Two prominent trade-offs in artificial intelligence are between predictive accuracy and fairness, and between predictive accuracy and interpretability.<n> prevailing interpretation views these formal trade-offs as directly corresponding to tensions between underlying social values.<n>I introduce a sociotechnical approach to examining the value implications of trade-offs.
  arXiv  Detail & Related papers  (2024-03-07T05:03:18Z)
• Towards Responsible AI in Banking: Addressing Bias for Fair Decision-Making [69.44075077934914]
  "Responsible AI" emphasizes the critical nature of addressing biases within the development of a corporate culture. This thesis is structured around three fundamental pillars: understanding bias, mitigating bias, and accounting for bias. In line with open-source principles, we have released Bias On Demand and FairView as accessible Python packages.
  arXiv  Detail & Related papers  (2024-01-13T14:07:09Z)
• Proceeding of the 1st Workshop on Social Robots Personalisation At the crossroads between engineering and humanities (CONCATENATE) [37.838596863193565]
  This workshop aims to raise an interdisciplinary discussion on personalisation in robotics. It aims at bringing researchers from different fields together to propose guidelines for personalisation.
  arXiv  Detail & Related papers  (2023-07-10T11:11:24Z)
• Rethinking Model Evaluation as Narrowing the Socio-Technical Gap [47.632123167141245]
  We argue that model evaluation practices must take on a critical task to cope with the challenges and responsibilities brought by this homogenization.<n>We urge the community to develop evaluation methods based on real-world contexts and human requirements.
  arXiv  Detail & Related papers  (2023-06-01T00:01:43Z)
• Ethical-Advice Taker: Do Language Models Understand Natural Language Interventions? [62.74872383104381]
  We investigate the effectiveness of natural language interventions for reading-comprehension systems. We propose a new language understanding task, Linguistic Ethical Interventions (LEI), where the goal is to amend a question-answering (QA) model's unethical behavior.
  arXiv  Detail & Related papers  (2021-06-02T20:57:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.