AWAI 2024 Abstracts

Area 1 - AWAI
Short Papers

Area 1 - AWAI

Short Papers
Paper Nr: 5
Title:

Towards Value Awareness in the Medical Field
Authors:

Manel Rodriguez-Soto, Nardine Osman, Carles Sierra, Paula Sánchez Veja, Rocio Cintas Garcia, Cristina Farriols Danes, Montserrat Garcia Retortillo and Silvia Minguez Maso
Abstract: This position paper aims to illustrate how models and mechanisms can be designed to support value-aware decision-making in the medical field. Such models and mechanisms allow for assessing the alignment of specific behaviours with human values, which could help medical personnel decide when to follow or break a protocol and help relevant boards decide when and how to update existing protocols. AI supporting decision-making in medicine is not new. Yet, AI that raises awareness about the alignment of medical decisions concerning human values is novel despite the vital importance of bioethics in the field. This paper presents a proposal for the formalisation of values and the design of models and mechanisms that raise value awareness in the medical field.
Download
Paper Nr: 6
Title:

Towards a Definition of Awareness for Embodied AI
Authors:

Giulio A. Abbo, Serena Marchesi, Kinga Ciupinska, Agnieszka Wykowska and Tony Belpaeme
Abstract: This paper explores the concept of awareness in the context of embodied artificial intelligence (AI), aiming to provide a practical definition and understanding of this multifaceted term. Acknowledging the diverse interpretations of awareness in various disciplines, the paper focuses specifically on the application of awareness in embodied AI systems. We introduce six foundational elements as essential building blocks for an aware embodied AI. These elements include access to information, information integration, attention, coherence, ex-plainability, and action. The interconnected and interdependent nature of these building blocks is emphasised, forming a minimal base for constructing AI systems with heightened awareness. The paper aims to spark a dialogue within the research community, inviting diverse perspectives to contribute to the evolving discipline of awareness in embodied AI. The proposed insights provide a starting point for further empirical studies and validations in real-world AI applications.
Download
Paper Nr: 7
Title:

Fine-Grained Clustering of Social Media: How Moral Triggers Drive Preferences and Consensus
Authors:

Emanuele Brugnoli, Pietro Gravino, Donald Ruggiero Lo Sardo, Vittorio Loreto and Giulio Prevedello
Abstract: The increased access to online information provided by social media platforms allows individuals to form and convey their beliefs regarding events in their daily lives. The wide range of interactions carried out in these virtual environments has the power to impact the decisions and behaviours of others, also creating conflict, polarisation, misinformation, and toxic content. When individuals engage in public debates about topics tied to significant societal concerns, these discussions often regard or imply moral values. By analyzing five years of Italian Twitter/X debate on immigration, we show how a language model aware of moral values detects community structures more accurately, better depicting the actual political scenario in Italy.
Download
Paper Nr: 8
Title:

Towards a Theory of Awareness
Authors:

Ricardo Sanz, Manuel Rodríguez, Martín Molina, Esther Aguado and Virgilio Gómez
Abstract: Observation of humans and animals shows that awareness is a critical aspect of mental processes for those agents that operate in changing environments. Responding to potentially dangerous situations and leveraging environmental affordances are essential capabilities for autonomous agents’ ecological viability. Agents need to be aware of their situations. Artificial autonomous systems construction depend on using suitable system architectures and applying proven engineering methods. While current systems display a certain degree of awareness, it is unclear what principles shall be used in their design. We are in a pre-scientific, pre-technological situation concering awareness. Unfortunately, the scientific analysis of the awareness phenomena is quite difficult because its principles cannot be easily isolated in fully functioning human minds. We need a clean, formal theory of general awareness of universal nature. This theory should be applicable both to humans and machines, and not exclusively bound to the psychology and neurobiology of living animals. In this position paper, the authors argue for developing such a theory, state some requirements for it and propose an initial conceptual seed for a future theory of awareness that orbit around the idea that awareness is the real-time understanding of sensory flows.
Download
Paper Nr: 9
Title:

An Ontology for Value Awareness Engineering
Authors:

Andrés Holgado-Sánchez, Holger Billhardt, Sascha Ossowski and Alberto Fernández
Abstract: The field of value awareness engineering claims that intelligent software agents should be endowed with a set of capabilities related to human values, enabling them to identify value-aligned outcomes and, ultimately, to choose their behaviour in value-aware manner. In this work we develop an ontology that links many of the models and concepts that have been proposed in relation to computational value awareness, so as to be able to formalize in a common language the various heterogeneous research proposals in the field. Specifically, we illustrate its capability for describing multi-agent systems from the value-awareness engineering perspective through several case studies grounded in concrete approaches from literature. The ontology, implemented in OWL and extended with SWRL rules, is evaluated following scenarios of the NeOn Methodology and is interconnected with relevant ontologies in the Semantic Web.
Download
Paper Nr: 10
Title:

Notes on Measures for Information Access in Neuroscience and AI Systems
Authors:

Giulio Prevedello, Luis Marcos-Vidal, Emanuele Brugnoli and Pietro Gravino
Abstract: With the increasing prevalence of artificial systems in society, it is imperative to ensure transparency in machine decision processes. To better elucidate their decisions, artificial systems must possess an awareness of the information they handle. This includes the understanding of information flow, integration and impact on the final outcome. A specific facet of awareness, termed access-consciousness, denotes the ability of information to be utilised in reasoning and the rational control of action (and speech). This study proposes a method for measuring access to information within a system by examining the communication dynamics among its components, specifically focusing on connectivity. To achieve this, we initially delineate the various types of connectivity in the brain and then propose their translation to artificial systems. Structural connections are highlighted as mechanisms enabling one component to access information from another. Additionally, we explore functional connectivity, which gauges the extent to which information from one component is utilised by another. Finally, operational connectivity is introduced to describe how information propagates from one component to the entire system. This framework aims to contribute to a clearer understanding of information access in both biological and artificial systems.
Download
Paper Nr: 11
Title:

AwarePrompt: Using Diffusion Models to Create Methods for Measuring Value-Aware AI Architectures
Authors:

Kinga Ciupinska, Serena Marchesi, Giulio A. Abbo, Tony Belpaeme and Agnieszka Wykowska
Abstract: The integration of diffusion models (DMs) into generative AI systems presents an approach with implications for ethical and moral AI development and our understanding of human-AI interaction. This study explores the intersection of generative AI, human values, and neuroscience, emphasizing the significance of value-awareness in AI systems. The methodology involves a behavioral experiment to evaluate the accuracy of DM-generated visual stimuli in capturing human values and related keywords. Results indicate promising match rates, marking stride in aligning AI systems with ethical and moral considerations. Additionally, the study introduces a criterion for selecting stimuli based on an “Aha” moment, setting the stage for an EEG experiment to explore the neural correlates associated with becoming aware of a value. This multidisciplinary study is a step toward the development of procedures to evaluate the effectiveness of Value-Aware AI systems in enhancing the perceived ethical and moral agency.
Download