Abstract: Human values, e.g., benevolence and self-determination, are the abstract motivations that drive our opinions and actions. AI agents ought to align their behavior with our value preferences to co-exist with us in our society. However, value preferences differ across individuals and are dependent on context. To reflect diversity in society and to align with contextual value preferences, AI agents must be able to discern the value preferences of the relevant individuals by interacting with them. We refer to this as the value inference challenge. Value inference entails several challenges and the related work is scattered across different AI subfields, from NLP to multiagent systems. We present a comprehensive overview of the value inference process by breaking it down into three distinct steps (value identification, classification, and estimation), introducing the related challenges and the methods we developed to address them. However, we recognize that relying solely on AI methods to infer values may not yield accurate estimates, due to the implicit nature of human value preferences. Humans must be actively engaged for a successful value inference. To this end, we propose a Hybrid Intelligence (HI) vision where human and artificial intelligence complement each other during the value inference process. We then introduce an HI approach that fosters self-reflection on values by connecting value classification and estimation. We conclude by describing several applications that are being developed based on value inference, ranging from support for deliberative policy-making to behavior change for diabetes patients. 

Publications:

• Value Inference in Sociotechnical Systems, In: Proc. of the 22nd International Conference on Autonomous Agents and Multiagent Systems, pp. 1774-1780, IFAAMAS, London, United Kingdom, 2023.
• What does a Text Classifier Learn about Morality? An Explainable Method for Cross-Domain Comparison of Moral Rhetoric, In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics, pp. 14113-14132, ACL, Toronto, Canada, 2023.
• Cross-Domain Classification of Moral Values, In: Findings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics, pp. 2727–2745, ACL, Seattle, WA, USA, 2022.
• Estimating Value Preferences in a Hybrid Participatory System, In: HHAI2022: Augmenting Human Intellect, pp. 114–127, IOS Press, Amsterdam, the Netherlands, 2022.
• HyEnA: A Hybrid Method for Extracting Arguments from Opinions, In: HHAI2022: Augmenting Human Intellect, pp. 17–31, IOS Press, Amsterdam, the Netherlands, 2022.
• What values should an agent align with?, In: Autonomous Agents and Multi-Agent Systems, vol. 36, no. 23, pp. 32, 2022.
• A Collaborative Platform for Identifying Context-Specific Values, In: Proceedings of the 20th International Conference on Autonomous Agents and Multiagent Systems, pp. 1773–1775, IFAAMAS, Online, 2021.
• Axies: Identifying and Evaluating Context-Specific Values, In: Proc. of the 20th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2021), pp. 799–808, IFAAMAS, Online, 2021.