With the growing capabilities and pervasiveness of AI systems, societies must collectively choose between reduced human autonomy, endangered democracies and limited human rights, and AI that is aligned to human and social values, nurturing collaboration, resilience, knowledge and ethical behaviour. In this chapter, we introduce the notion of self-reflective AI systems for meaningful human control over AI systems. Focusing on decision support systems, we propose a framework that integrates knowledge from psychology and philosophy with formal reasoning methods and machine learning approaches to create AI systems responsive to human values and social norms. We also propose a possible research approach to design and develop self-reflective capability in AI systems. Finally, we argue that self-reflective AI systems can lead to self-reflective hybrid systems (human + AI), thus increasing meaningful human control and empowering human moral reasoning by providing comprehensible information and insights on possible human moral blind spots. @en

We adopt an emerging and prominent vision of human-centred Artificial Intelligence that requires building trustworthy intelligent systems. Such systems should be capable of dealing with the challenges of an interconnected, globalised world by handling plurality and by abiding by human values. Within this vision, pluralistic value alignment is a core problem for AI– that is, the challenge of creating AI systems that align with a set of diverse individual value systems. So far, most literature on value alignment has considered alignment to a single value system. To address this research gap, we propose a novel method for estimating and aggregating multiple individual value systems. We rely on recent results in the social choice literature and formalise the value system aggregation problem as an optimisation problem. We then cast this problem as an ℓ_p-regression problem. Doing so provides a principled and general theoretical framework to model and solve the aggregation problem. Our aggregation method allows us to consider a range of ethical principles, from utilitarian (maximum utility) to egalitarian (maximum fairness). We illustrate the aggregation of value systems by considering real-world data from two case studies: the Participatory Value Evaluation process and the European Values Study. Our experimental evaluation shows how different consensus value systems can be obtained depending on the ethical principle of choice, leading to practical insights for a decision-maker on how to perform value system aggregation.

@en

Hypertension is a condition affecting most people over 45 years old. Health Self-Management offers many opportunities for prevention and cure. However, most scientific health literature is unknown by health professionals and/or patients. Per year about 200.000 new scientific papers on cardiovascular health appear, which is too much for a human to read. Hence, an LLM-based Health AI research assistant is developed for mining scientific literature on blood pressure and food. A user evaluation was conducted with n=8 participants who just completed an intensive lifestyle intervention for blood pressure self-management. They highlighted several challenges and opportunities for a Health AI, especially regarding claim transparency, data quality and risks of hallucinations. In the discussion we propose seven criteria using metadata and information characteristics to help evaluate ambiguous or conflicting health science claims. @en

Large-scale survey tools enable the collection of citizen feedback in opinion corpora. Extracting the key arguments from a large and noisy set of opinions helps in understanding the opinions quickly and accurately. Fully automated methods can extract arguments but (1) require large labeled datasets that induce large annotation costs and (2) work well for known viewpoints, but not for novel points of view. We propose HyEnA, a hybrid (human + AI) method for extracting arguments from opinionated texts, combining the speed of automated processing with the understanding and reasoning capabilities of humans. We evaluate HyEnA on three citizen feedback corpora. We find that, on the one hand, HyEnA achieves higher coverage and precision than a state-of-The-Art automated method when compared to a common set of diverse opinions, justifying the need for human insight. On the other hand, HyEnA requires less human effort and does not compromise quality compared to (fully manual) expert analysis, demonstrating the benefit of combining human and artificial intelligence.

@en

Disagreements are common in online societal deliberation and may be crucial for effective collaboration, for instance in helping users understand opposing viewpoints. Although there exist automated methods for recognizing disagreement, a deeper understanding of factors that influence disagreement is currently missing. We investigate a hypothesis that differences in personal values influence disagreement in online discussions. Using Large Language Models (LLMs) for estimating both profiles of personal values and disagreement, we conduct a large-scale experiment involving 11.4M user comments. We find that the dissimilarity of value profiles correlates with disagreement only in specific cases, but that incorporating self-reported value profiles changes these results to be more undecided.@en

Presenting high-level arguments is a crucial task for fostering participation in online societal discussions. Current argument summarization approaches miss an important facet of this task-capturing diversity-which is important for accommodating multiple perspectives. We introduce three aspects of diversity: those of opinions, annotators, and sources. We evaluate approaches to a popular argument summarization task called Key Point Analysis, which shows how these approaches struggle to (1) represent arguments shared by few people, (2) deal with data from various sources, and (3) align with subjectivity in human-provided annotations. We find that both general-purpose LLMs and dedicated KPA models exhibit this behavior, but have complementary strengths. Further, we observe that diversification of training data may ameliorate generalization. Addressing diversity in argument summarization requires a mix of strategies to deal with subjectivity.

@en

The expressive power and effectiveness of large language models (LLMs) is going to increasingly push intelligent agents towards sub-symbolic models for natural language processing (NLP) tasks in human–agent interaction. However, LLMs are characterised by a performance vs. transparency trade-off that hinders their applicability to such sensitive scenarios. This is the main reason behind many approaches focusing on local post-hoc explanations, recently proposed by the XAI community in the NLP realm. However, to the best of our knowledge, a thorough comparison among available explainability techniques is currently missing, as well as approaches for constructing global post-hoc explanations leveraging the local information. This is why we propose a novel framework for comparing state-of-the-art local post-hoc explanation mechanisms and for extracting logic programs surrogating LLMs. Our experiments—over a wide variety of text classification tasks—show how most local post-hoc explainers are loosely correlated, highlighting substantial discrepancies in their results. By relying on the proposed novel framework, we also show how it is possible to extract faithful and efficient global explanations for the original LLM over multiple tasks, enabling explainable and resource-friendly AI techniques.@en

Channel allocation in dense Wi-Fi networks is a complex problem due to its nonlinear and exponentially sized solution space. Negotiating over this domain is a challenge, since it is difficult to estimate opponent’s utility. Based on our previous work in mediated techniques, we propose the first two fully-distributed multi-agent negotiations for Wi-Fi channel assignment. Both of them use a simulated annealing sampling process and a noisy model graph estimation. One is designed for Alternating Offers protocols, while the other uses the novel Multiple Offers Protocol for Multilateral Negotiations with Partial Consensus (MOPaC), with experimental promising features for our particular domain. Our experiments compare both proposals against their mediated counterparts, showing similar results on social welfare, Nash product and fairness, but improving privacy and communication overhead.

@en

Values, such as freedom and safety, are the core motivations that guide us humans. A prerequisite for creating value-aligned multiagent systems that involve humans and artificial agents is value inference, the process of identifying values and reasoning about human value preferences. We introduce a framework that connects the value inference steps, and motivate why a hybrid intelligence approach is instrumental for its success. We also highlight the multidisciplinary research challenges that hybrid value inference entails.

@en

We present a review that unifies decision-support methods for exploring the solutions produced by multi-objective optimization (MOO) algorithms. As MOO is applied to solve diverse problems, approaches for analyzing the trade-offs offered by MOO algorithms are scattered across fields. We provide an overview of the advances on this topic, including methods for visualization, mining the solution set, and uncertainty exploration as well as emerging research directions, including interactivity, explainability, and ethics. We synthesize these methods drawing from different fields of research to build a unified approach, independent of the application. Our goals are to reduce the entry barrier for researchers and practitioners on using MOO algorithms and to provide novel research directions.@en

Although popular and effective, large language models (LLM) are characterised by a performance vs. transparency trade-off that hinders their applicability to sensitive scenarios. This is the main reason behind many approaches focusing on local post-hoc explanations recently proposed by the XAI community. However, to the best of our knowledge, a thorough comparison among available explainability techniques is currently missing, mainly for the lack of a general metric to measure their benefits. We compare state-of-the-art local post-hoc explanation mechanisms for models trained over moral value classification tasks based on a measure of correlation. By relying on a novel framework for comparing global impact scores, our experiments show how most local post-hoc explainers are loosely correlated, and highlight huge discrepancies in their results—their “quarrel” about explanations. Finally, we compare the impact scores distribution obtained from each local post-hoc explainer with human-made dictionaries, and point out that there is no correlation between explanation outputs and the concepts humans consider as salient.

@en

Channel allocation in dense, decentralized Wi-Fi networks is a challenging due to the highly nonlinear solution space and the difficulty to estimate the opponent’s utility model. So far, only centralized or mediated approaches have succeeded in applying negotiation to this setting. We propose the first two fully-distributed negotiation approaches for Wi-Fi channel assignment. Both of them leverage a pre-sampling of the utility space with simulated annealing and a noisy estimation of the Wi-Fi utility function. Regarding negotiation protocols, one of the approaches makes use of the Alternating Offers protocol, while the other uses the novel Multiple Offers Protocol for Multilateral Negotiations with Partial Consensus (MOPaC), which naturally matches the problem peculiarities. We compare the performance of our proposed approaches with the previous mediated approach, based on simple text mediation. Our experiments show that our approaches yield better utility outcomes, better fairness and less information disclosure than the mediated approach.

@en

As smart cities increasingly become real, an ethical framework for them becomes increasingly necessary. Surprisingly, current approaches largely disregard such a framework and concentrate primarily on challenges pertaining to the data lifecycle. However, a smart city involves much more than data gathering: it involves the interactions of residents, businesses, and government agencies with respect to public and private resources subject to potentially subtle regulations and other norms. This article introduces a sociotechnical view of smart cities and shows how it may be profitably mapped to the moral foundation theory to provide a comprehensive ethical framework.

@en

As artificial agents become increasingly embedded in our society, we must ensure that their behavior aligns with human values. Value alignment entails value inference, the process of identifying values and reasoning about how humans prioritize values. We introduce a holistic framework that connects the technical (AI) components necessary for value inference. Subsequently, we discuss how hybrid intelligence'the synergy of human and artificial intelligence'is instrumental to the success of value inference. Finally, we illustrate how value inference both poses significant challenges and provides novel opportunities for multiagent systems research.@en

User experience is the ultimate quality of service criterion for modern WLAN networks. However, network configuration approaches are mainly network-centric. We envision a paradigm shift, empowering users in network management. We study how automated negotiation and collective intelligence can support the democratic configuration of a wireless network, leveraging client and provider interests. This new paradigm allows for flexible network configuration, which enables better exploitation of resources considering the clients real usage and needs, and a fair distribution of throughput among users.

@en

The pursuit of values drives human behavior and promotes cooperation. Existing research is focused on general values (e.g., Schwartz) that transcend contexts. However, context-specific values are necessary to (1) understand human decisions, and (2) engineer intelligent agents that can elicit and align with human values. We propose Axies, a hybrid (human and AI) methodology to identify context-specific values. Axies simplifies the abstract task of value identification as a guided value annotation process involving human annotators. Axies exploits the growing availability of value-laden text corpora and Natural Language Processing to assist the annotators in systematically identifying context-specific values. We evaluate Axies in a user study involving 80 human subjects. In our study, six annotators generate value lists for two timely and important contexts: Covid-19 measures and sustainable Energy. We employ two policy experts and 72 crowd workers to evaluate Axies value lists and compare them to a list of general (Schwartz) values. We find that Axies yields values that are (1) more context-specific than general values, (2) more suitable for value annotation than general values, and (3) independent of the people applying the methodology.@en

The key arguments underlying a large and noisy set of opinions help understand the opinions quickly and accurately. Fully automated methods can extract arguments but (1) require large labeled datasets and (2) work well for known viewpoints, but not for novel points of view. We propose HyEnA, a hybrid (human + AI) method for extracting arguments from opinionated texts, combining the speed of automated processing with the understanding and reasoning capabilities of humans. We evaluate HyEnA on three feedback corpora. We find that, on the one hand, HyEnA achieves higher coverage and precision than a state-of-the-art automated method, when compared on a common set of diverse opinions, justifying the need for human insight. On the other hand, HyEnA requires less human effort and does not compromise quality compared to (fully manual) expert analysis, demonstrating the benefit of combining human and machine intelligence.

@en