PhD Research

This section contains all my research interests / projects

Publications

#

• Helpful, harmless, honest? Sociotechnical limits of AI alignment and safety through Reinforcement Learning from Human Feedback A Dahlgren Lindström, L Methnani, L Krause, P Ericson, … Ethics and Information Technology 27 (2), 28, 2025. New!
• Designing Explainable and Counterfactual-Based AI Interfaces for Operators in Process Industries Y Zhang, L Methnani, E Brorsson, E Zohrevandi, A Darnell, K Kucher VISIGRAPP 2025: 20th International Joint Conference on Computer Vision …, 2025.
• PRISM: A Pragmatic Framework for Evaluating Counterfactual Explanations in XAI L Methnani, V Dignum, A Theodorou AAAI 2025 Workshop on AI Governance: Alignment, Morality, and Law, 2025.
• AI alignment through reinforcement learning from human feedback? Contradictions and limitations AD Lindström, L Methnani, L Krause, P Ericson, ÍMR de Troya, DC Mollo, … arXiv preprint arXiv:2406.18346, 2024.
• Who’s in charge here? a survey on trustworthy ai in variable autonomy robotic systems L Methnani, M Chiou, V Dignum, A Theodorou ACM computing surveys 56 (7), 1-32, 2024.
• Human-centered Explainable-AI: An empirical study in Process industry Y Zhang, E Brorsson, L Methnani, E Zohrevandi, N Bhattacharya, … Artificial Intelligence and Social Computing 122 (122), 2024.
• The impact of Mixed-Initiative on collaboration in hybrid AI L Methnani, A Dahlgren Lindström, V Dignum HHAI 2024: Hybrid Human AI Systems for the Social Good, 469-471, 2024.
• Clash of the Explainers: Argumentation for Context-Appropriate Explanations L Methnani, V Dignum, A Theodorou European Conference on Artificial Intelligence, 7-23, 2023.
• Embracing AWKWARD! Real-Time Adjustment of Reactive Plans Using Social Norms L Methnani, A Antoniades, A Theodorou International Workshop on Coordination, Organizations, Institutions, Norms …, 2022.
• Embracing AWKWARD! A Hybrid Architecture for Adjustable Socially-Aware Agents L Methnani Thesis.
• Operationalising AI ethics: conducting socio-technical assessment L Methnani, M Brännström, A Theodorou ECCAI Advanced Course on Artificial Intelligence, 304-321, 2021.
• Let me take over: Variable autonomy for meaningful human control L Methnani, A Aler Tubella, V Dignum, A Theodorou Frontiers in Artificial Intelligence 4, 737072, 2021.

Talks

#

• Introduction to Responsible and Explainable AI (REX) Tutorial | XAI Lecture Northern Lights Deep Learning (NLDL) Winter School Jan 2025.
• Explainable AI is a double-edged sword Lightning Talk at Women in Data Science, AI & ML (WiDS) Sweden Mar 2024