Publications
We present here publications by students (highlighted in bold) from the UKRI Centre for Doctoral Training in Safe and Trusted Artificial Intelligence (grant reference number EP/S023356/1).
2024
Battogtokh, M., Xing, Y., Davidescu, C., Abdul-Rahman, A., Luck, M. & Borgo, R. (2024). Visual Analytics for Fine-grained Text Classification Models and Datasets. Computer Graphics Forum, Volume 43.
Battogtokh, M., Davidescu, C., Luck, M. & Borgo, R. (2024). SemLa: A Visual Analysis System for Fine-grained Text Classification. In Proceedings of the 38th AAAI Conference on Artificial Intelligence (AAAI 2024).
Bristow, T., Thorburn, L., & Acosta-Navas, D. (2024). Views on AI Aren’t Binary — They’re Plural. In Proceedings of the 7th AAAI/ACM Conference on AI, Ethics, and Society (AIES 2024).
Cope, D. & McBurney, P. (2024). Learning Translations: Emergent Communication Pretraining for Cooperative Language Acquisition. In Proceedings of the 33rd International Joint Conference on Artificial Intelligence (IJCAI 2024).
Cope, D. & McBurney, P. (2024). Mimicry and the Emergence of Cooperative Communication. In Proceedings of the 2024 International Conference on Artificial Life (ALIFE 2024).
Curtis, S., Iyer, R., Domenico Kirk-Giannini, C., Krakovna, V., Krueger, D., Lambert, N., Marnette, B., McKenzie, C., Michael, J., Miyazono, E., Mima, N., Ovadya, A., Thorburn, L., & Turan, D. (2024). Research Agenda for Sociotechnical Approaches to AI Safety. AI Objectives Institute.
Gausen, A., Guo, C. & Luk, W. (2024). An approach to sociotechnical transparency of social media algorithms using agent-based modelling. AI Ethics.
Gausen, A., Mitra, B., & Lindley, S. (2024). A Framework for Exploring the Consequences of AI-Mediated Enterprise Knowledge Access and Identifying Risks to Workers. In Proceedings of the 7th ACM Conference on Fairness, Accountability, and Transparency (FAccT 2024).
Gavenski, N., Luck, M., & Rodrigues, O. (2024). Imitation Learning Datasets: A Toolkit For Creating Datasets, Training Agents and Benchmarking. In Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2024).
Gavenski, N., Monteiro, J., Meneguzzi, F., Luck, M. & Rodrigues, O. (2024). Explorative Imitation Learning: A Path Signature Approach for Continuous Environments. In Proceedings of the 27th European Conference on Artificial Intelligence (ECAI 2024).
Goodall, A. W. & Belardinelli, F. (2024) Leveraging Approximate Model-based Shielding for Probabilistic Safety Guarantees in Continuous Environments. In Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent System (AAMAS 2024).
Kori, A., Locatello, F., and Ribeiro, F., Toni, F., & Glocker, B. (2024). Grounded Object-Centric Learning. In Proceedings of the 12th International Conference on Learning Representations (ICLR 2024).
Kori, A., Locatello, F., Santhirasekaram, A., Toni, F., Glocker, B., & Riberio, F. (2024). Identifiable Object-Centric Representation Learning via Probabilistic Slot Attention. In Proceedings of the 38th Annual Conference on Neural Information Processing Systems (NeurIPS 2024).
Leslie, D., Ashurst, C., Gonzalez, N. M., Griffiths, F., Jayadeva, S., Jorgensen, M., Katell, M., Krishna, S., Kwiatkowski, D., Martins, C. I., Mahomed, S., Mougan, C., Pandit, S., Richey, M., Sakshaug, J. W., Vallor, S., Vilain, L. (2024). ‘Frontier AI,’ Power, and the Public Interest: Who Benefits, Who Decides?. Harvard Data Science Review, Special Issue 5.
Lubin, N., Mayberry, K., Moses, D., Revel, M., Thorburn, L., & West, A. (2024) Mapping the space of social media regulation. MIT Science Policy Review, Volume 5.
Lubin, N., Mayberry, K., Revel, M., & Thorburn, L. (2024). Underexplored Ways to Regulate Social Media. Tech Policy Press.
Parac, R., Nodari, L., Ardon, L., Furelos-Blanco, D., Cerutti, F., & Russo, A. (2024). Learning Robust Reward Machines from Noisy Labels (pre-print). In Proceedings of the 21st International Conference on Principles of Knowledge Representation and Reasoning (KR 2024).
Pavlova, M., Casey, B., & Wang, M. (2024). ESG-FTSE: A Corpus of News Articles with ESG Relevance Labels and Use Cases. In Proceedings of the Joint Workshop of the 7th Financial Technology and Natural Language Processing (FinNLP 2024), the 5th Knowledge Discovery from Unstructured Data in Financial Services, and the 4th Workshop on Economics and Natural Language Processing.
Roesch, S., Leonardos, S. & Du, Y. (2024). The Selfishness Level of Social Dilemmas. In Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2024).
Szabo, J., Criado, N., Such, J., & Modgil, S. (2024). Moral Uncertainty and the Problem of Fanaticism. In Proceedings of the 38th AAAI Conference on Artificial Intelligence (AAAI 2024).
Thorburn, L., Stray, J., & Bengani, P. (2024). Experiments are the Best Kind of Transparency. Tech Policy Press.
Thorburn, L., Polukarov, M., & Ventre, C. (2024). Societal Sorting as a Systemic Risk of Recommenders. In Proceedings of the 18th ACM Conference on Recommender Systems (RecSys 2024).
Tisnikar, P., Canal, G. & Leonetti, M. (2024). Probabilistic Inference of Human Capabilities from Passive Observations. In Proceedings of the 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2024).
Wachowiak, L., Coles, A., Celiktutan, O., & Canal, G. (2024). Are Large Language Models Aligned with People’s Social Intuitions for Human-Robot Interactions? In Proceedings of the 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2024)
Wachowiak, L., Fenn, A., Kamran, H., Coles, A., Celiktutan, O., & Canal, G. (2024). When Do People Want an Explanation from a Robot?. In Proceedings of the 19th Annual ACM/IEEE International Conference on Human-Robot Interaction (HRI 2024).
Wachowiak, L., Tisnikar, P., Canal, G., Coles, A., Leonetti, M., & Celiktutan, O. (2024). Predicting When and What to Explain From Multimodal Eye Tracking and Task Signals. IEEE Transactions on Affective Computing.
Wachowiak, L., Tisnikar, P., Coles, A., Canal, G., & Celiktutan, O. (2024). A Time Series Classification Pipeline for Detecting Interaction Ruptures in HRI Based on User Reactions. In Proceedings of the 26th International Conference on Multimodal Interaction (ICMI 2024).
Wachowiak, L., Coles, A., Canal, G., & Celiktutan, O. (2024). A Taxonomy of Explanation Types and Need Indicators in Human–Agent Collaborations. International Journal of Social Robotics, Volume 16, pages 1681–1692.
Ward, F. W., MacDermott, M., Belardinelli, F., Toni, F. & Everitt, T. (2024). The Reasons that Agents Act: Intention and Instrumental Goals. In Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2024).
Waller, M., Rodrigues, O., & Cocarascu, O. (2024). Identifying Reasons for Bias: An Argumentation-Based Approach. In Proceedings of the AAAI Technical Track on Safe, Robust and Responsible AI, held at the 38th AAAI Conference on Artificial Intelligence (AAAI 2024)
Wicke, P. & Wachowiak, L. (2024). Exploring Spatial Schema Intuitions in Large Language and Vision Models. In Findings of the Association for Computational Linguistics (ACL 2024).
Willis, R., Du, Y., Leibo, J.Z. et al. (2024) Resolving social dilemmas with minimal reward transfer. Autonomous Agents and Multiagent Systems, Volume 38.
Wu, W., Pierazzi, F., Du, Y., & Brandão, M. (2024). Characterizing Physical Adversarial Attacks on Robot Motion Planners. In Proceedings of the 41st IEEE International Conference on Robotics and Automation (ICRA 2024).
2023
Armitage, R., Gallacher, J., Gu, J., Hogan, A., Howard, P., Kollanyi, B., Kuchta, R., Neudert, L., & Thorburn, L. (alphabetical). (2023). Evaluating Recommender Systems in Relation to the Dissemination of Illegal and Harmful Content in the UK. A report by Pattrn Analytics & Intelligence (Pattrn.AI) for Ofcom.
Attanasio, G., Pastor, E., Di Bonaventura, C., & Nozza, D. (2023). ferret: a Framework for Benchmarking Explainers on Transformers. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations (EACL 2023).
Battogtokh, M., Luck, M., Davidescu, C. & Borgo, R. (2023). Simple Framework for Interpretable Fine-grained Text Classification. In Proceedings of the 3rd International Workshop on Explainable and Interpretable Machine Learning (XI-ML 2023), held at the 26th European Conference on Artificial Intelligence (ECAI 2023).
Bengani, P., Stray, J., & Thorburn, L. (2023) What is Media Diversity and Do Recommender Systems Have It? Tech Policy Press.
Bezou-Vrakatseli, E., Brückner, B. & Thorburn, L. (2023). SHAPE: A Framework for Evaluating the Ethicality of Influence. In Proceedings of the 20th European Conference on Multi-Agent Systems (EUMAS 2023).
Bezou-Vrakatseli, E. (2023). Evaluation of LLM Reasoning via Argument Schemes. Online Handbook of Argumentation for AI, Vol. 4.
Cope, D. (2023). Real-time Evolution of Multicellularity with Artificial Gene Regulation. In Proceedings of the 2023 Conference on Artificial Life (ALIFE 2023).
Cope, D., Svegliato, J. & Russell, S. (2023). Learning to Plan with Tree Search via Deep RL. In Proceedings of the Bridging the Gap Between AI Planning and Reinforcement Learning Workshop (PRL 2023), held at the 22nd International Joint Conference on Artificial Intelligence (IJCAI 2023).
Di Bonaventura, C., Muti, A., & Stranisci, M.A. (2023). O-Dang at HODI and HaSpeeDe3: A Knowledge-Enhanced Approach to Homotransphobia and Hate Speech Detection in Italian. In Proceedings of the 8th Evaluation Campaign of Natural Language Processing and Speech Tools for Italian (EVALITA 2023).
Fox, J., MacDermott, M., Hammond, L., Harrenstein, P., Abate, A., & Wooldridge, M. (2023). On Imperfect Recall in Multi-Agent Influence Diagrams. In Proceedings of the 19th Conference on Theoretical Aspects of Rationality and Knowledge (TARK 2023).
Goodall, A. W. & Belardinelli, F. (2023). Approximate Model-Based Shielding for Safe Reinforcement Learning. In Proceedings of the 26th European Conference on Artificial Intelligence (ECAI 2023).
Goodall, A. W., & Belardinelli, F. (2023). Approximate Shielding of Atari Agents for Safe Exploration. In Proceedings of the Adaptive and Learning Agents Workshop (ALA 2023), held at the 22nd International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2023).
Henriksen, P., & Lomuscio, A. (2023). Robust Training of Neural Networks Against Bias Field Perturbations. In Proceedings of the 37th AAAI Conference on Artificial Intelligence (AAAI 2023).
Hussain, A, Leonte, D., Belardinelli, F., & Piliouras, G. (2023). Stability of Multi-Agent Learning: Convergence in Network Games with Many Players. In Proceedings of the Workshop on New Frontiers in Learning, Control, and Dynamical Systems, held at the 40th International Conference on Machine Learning (ICML 2023).
Jackson, A., Schoots, N., Luck, M., & Black, E. (2023). Neuroevolutionary Ticket Search — Finding Sparse, Trainable DNN Initialisations. In Proceedings of the Workshop on Sparsity in Neural Networks, held at the 11th International Conference on Learning Representations (ICLR 2023).
Jackson, A., Schoots, N., Ahantab, A., Luck, M., & Black, E. (2023). Finding Sparse Initialisations using Neuroevolutionary Ticket Search (NeTS). In Proceedings of the 2023 Conference on Artificial Life (ALIFE 2023).
Jorgensen, M., Richert, H., Black, E., Criado, N., & Such, J. (2023). Not So Fair: The Impact of Presumably Fair Machine Learning Models. In Proceedings of the 6th AAAI/ACM Conference on AI, Ethics, and Society (AIES 2023).
Jorgensen, M., Waller, M., Cocarascu, O., Criado, N., Rodrigues, O., Such, J., Black, E. (2023). Investigating the Legality of Bias Mitigation Methods in the United Kingdom. IEEE Technology and Society Magazine (Volume: 42, Issue: 4, December 2023).
Kenton, Z., Kumar, R., Farquhar, S., Richens, J., MacDermott, M., & Everitt, T. (2023). Discovering Agents. Artificial Intelligence, Volume 322, 103963.
Kori, A., Glocker, B., & Toni, F. (2023). GLANCE: Global to Local Architecture-Neutral Concept-based Explanations. In Proceedings of the 1st Workshop on XAI in Action: Past, Present, and Future Applications, held at the 37th Annual Conference on Neural Information Processing Systems (NeurIPS 2023).
Kori, A., Sanchez, P., Vilouras, K., Glocker, B., & Tsaftaris, S. (2023). A Causal Ordering Prior for Unsupervised Representation Learning. In Proceedings of the 3rd workshop on Causal Representation Learning Workshop, held at the 37th Annual Conference on Neural Information Processing Systems (NeurIPS 2023).
Laha, R., Wu, W., Sun, R., Mansfeld, N., Figueredo, L. F., & Haddadin, S. (2023). S*: On Safe and Time Efficient Robot Motion Planning. In Proceedings of the 40th IEEE International Conference on Robotics and Automation (ICRA 2023).
Lan, J., Brückner, B. & Lomuscio, A. (2023). A Semidefinite Relaxation Based Branch-and-Bound Method for Tight Neural Network Verification. In Proceedings of the AAAI 37th Conference on Artificial Intelligence (AAAI 2023).
MacDermott, M., Belardinelli, F. & Everitt, T. (2023) Decision Theory using Mechanised Causal Graphs. In Proceedings of the 5th Games, Agents and Incentives Workshop (GAIW 2023), held at the 22nd International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2023).
Monteiro, J., Gavenski, N., F. Meneguzzi, F. & Barros, R. C and R. C. Barros, “Self-Supervised Adversarial Imitation Learning. (2023). In Proceedings of the International Joint Conference on Neural Networks (IJCNN 2023).
Ovadya, A. & Thorburn, L. (2023) Bridging Systems: Open Problems for Countering Destructive Divisiveness Across Ranking, Recommenders and Governance. 23-11 Knight First Amend. Inst.
Ouyang, S., Zhang, J. M., Harman, M., & Wang, M. (2023). An Empirical Study of the Non-determinism of ChatGPT in Code Generation. ACM Transactions on Software Engineering and Methodology.
Parraga, O., D. More, M., Oliveira, C. M., Gavenski, N., Kupssinskü, L., Medronha, A., Moura, L., Simões, G., & Barros, R. (2023). Fairness in Deep Learning: A Survey on Vision and Language Research. ACM Computer Surveys.
Rader, A. P. & Russo, A. (2023). Active Learning in Neurosymbolic AI with Embed2Sym. In Proceedings of the International Workshop on Cognitive AI (CogAI 2023), held at the 3rd International Conference on Learning & Reasoning (IJCLR 2023).
Rago, A., Russo, F., Albini, E., Baroni, P., & Toni, F. (2023) Explaining Classifiers’ Output with Causal Models and Argumentation. Journal of Applied Logics – IfCoLog Journal of Logics and their Applications, Volume 10, Number 3, pages 421-449.
Russo, F. (2023). Argumentation for Interactive Causal Discovery. In Proceedings of the IJCAI 2023 Doctoral Consortium, held at the 32nd International Joint Conference on Artificial Intelligence (IJCAI 2023).
Russo, F., & Toni, F. (2023). Causal Discovery and Knowledge Injection for Contestable Neural Networks. In Proceedings of the 26th European Conference on Artificial Intelligence (ECAI 2023).
Sahbane, I., Ward, F. R. & Åslund, C. H. (2023). Experiments with Detecting and Mitigating AI Deception. In Proceedings of the Workshop on Safe and Trustworthy AI (STAI 2023), held at the 39th International Conference on Logic Programming (ICLP 2023).
Santhirasekaram, A., Kori, A., Winkler, M., Rockall, A., Toni, F., & Glocker, B. (2023). Robust Hierarchical Symbolic Explanations in Hyperbolic Space for Image Classification. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW 2023)
Schoots, N. & Cope, D. (2023). Low-Entropy Latent Variables Hurt Out-of-Distribution Performance. In Proceedings of the Workshop on Domain Generalization (DG 2023), held at the 11th International Conference on Learning Representations (ICLR 2023).
Thorburn, L., Bristow, T. & Carroll, L. (2023). Response to Safe and Responsible AI in Australia discussion paper, published by the Australian Government Department of Industry, Science and Resources.
Thorburn, L., Polukarov, M. & Ventre, C. (2023). Polarization as Probabilistic Dependence. In Proceedings of the 9th International Workshop on Computational Social Choice (COMSOC 2023).
Thorburn, L., Polukarov, M. & Ventre, C. (2023). Error in the Euclidean Preference Model. In Proceedings of the 22nd International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2023).
Thorburn, L., Polukarov, M., & Ventre, C. (2023). Error in the Euclidean Preference Model. In Proceedings of the 32nd International Joint Conference on Artificial Intelligence (IJCAI 2023).
Thorburn, L. & Ovadya, A. (2023). How to redesign social media algorithms to bridge divides. The Conversation.
Thorburn, L., Stray, J., & Bengani, P. (2023). Making Amplification Measurable. Tech Policy Press.
Thorburn, L., Stray, J., & Bengani, P. (2023) What’s the Difference Between Search and Recommendation? Tech Policy Press.
Thorburn, L., Stray, J., & Bengani, P. (2023) When You Hear “Filter Bubble”, “Echo Chamber”, or “Rabbit Hole” — Think “Feedback Loop”. Medium.
Wachowiak, L., Celiktutan, O., Coles, A., & Canal, G. (2023). A Survey of Evaluation Methods and Metrics for Explanations in Human–Robot Interaction (HRI). In Proceedings of the Explainable Robotics Workshop, held at the 44th IEEE International Conference on Robotics and Automation (ICRA 2023).
Wachowiak, L., & Gromann, D. (2023). Does GPT-3 Grasp Metaphors? Identifying Metaphor Mappings with Generative Language Models. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL 2023).
Wachowiak, L. & Gromann, D. & Xu, C. (2023) The Image Schema VERTICALITY: Definitions-and Annotation Guidelines. In The Seventh Image Schema Day, held at the 20th International Conference on Principles of Knowledge Representation and Reasoning (KR 2023).
Waller, M., Rodrigues, O. & Cocarascu, O. (2023). Recommendations for Bias Mitigation Methods: Applicability and Legality. In Proceedings of the 1st AEQUITAS Workshop on Fairness and Bias in AI, held at the 26th European Conference on Artificial Intelligence (ECAI 2023).
Ward, F. R., Toni, F., & Belardinelli, F. (2023). Defining Deception in Structural Causal Games (Extended Abstract). In Proceedings of the 22nd International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2023).
Willis, R. & Luck, M. (2023). Resolving Social Dilemmas through Reward Transfer Commitments. In Proceedings of the 15th Adaptive and Learning Agents Workshop (ALA 2023), held at the 22nd International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2023).
Yang, A., Robeyns, M., Milsom, E., Anson, B., Schoots, N., & Aitchison, L. (2023). A Theory of Representation Learning Gives a Deep Generalisation of Kernel Methods. In Proceedings of the 40th International Conference on Machine Learning (ICML 2023).
2022
Bengani, P., Stray, J., & Thorburn, L. (2022). A Menu of Recommender Transparency Options. Tech Policy Press.
Bengani, P., Stray, J., & Thorburn, L. (2022). What’s Right and What’s Wrong with Optimizing for Engagement. Medium.
Bezou-Vrakatseli, E. (2022). Debating Ethics: Using Argumentation to Support Dialogue. Online Handbook of Argumentation for AI, Vol 3.
Bezou-Vrakatseli, E., Cocarascu, O., & Modgil, S. (2022). Towards an Argument Scheme Classification for Ethical Reasoning. In Proceedings of the 22nd Workshop on Computational Models of Natural Argument (CMNA 2022), held at the 9th International Conference on Computational Models of Argument (COMMA 2022).
Cope, D. & McBurney, P. (2022). Joining the Conversation: Towards Language Acquisition for Ad Hoc Team Play. In Proceedings of the Workshop on Emergent Communication (EmeCom 2022), held at the 10th International Conference on Learning Representations (ICLR 2022).
Gausen, A., Luk, W. and Guo, C. (2022). Using Agent-Based Modelling to Evaluate the Impact of Algorithmic Curation on Social Media. ACM Journal of Data and Information Quality, Volume 15, Issue 1, pages 1-24.
Gromann, D., Wachowiak, L., Lang, C., & Heinisch, B. (2022). Extracting Terminological Concept Systems from Natural Language Text. In Rehm, G. (eds) European Language Grid. Springer.
Hussain, A., & Belardinelli, F. (2022). Equilibria and Convergence of Fictitious Play on Network Aggregative Games. In Proceedings of the Workshop on Adaptive and Learning Agents (ALA 2022), held at the 21st International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2022).
Henriksen, P., Leofante, F., & Lomuscio, A. (2022). Repairing Misclassifications in Neural Networks Using Limited Data. In Proceedings of the 37th ACM/SIGAPP Symposium On Applied Computing (SAC 2022).
Jorgensen, M., Black, E., Criado, N., & Such, J. (2022). Supposedly Fair Classification Systems and Their Impacts. In Proceedings of the 2nd Workshop on Adverse Impacts and Collateral Effects of Artificial Intelligence Technologies (AIofAI 2022), held at the 31st International Conference on Artificial Intelligence (IJCAI 2022).
Leofante, F., Henriksen, P., & Lomuscio, A. (2022). Verification-Friendly Networks: The Case for Parametric ReLUs. In Proceedings of the 1st Workshop on Formal Verification of Machine Learning (WFVML2022), held at the 39th International Conference on Machine Learning (ICML 2022).
McGillivray, B., Alahapperuma, M., Cook, J., Di Bonaventura, C., Meroño-Peñuela, A., Tyson, G., & Wilson, S. (2022). Leveraging Time-Dependent Lexical Features for Offensive Language Detection. In Proceedings of the 1st Workshop on Ever Evolving NLP (EvoNLP 2022).
Santhirasekaram, A., Kori, A., Winkler, M., Rockall, A. & Glocker, B. (2022). Vector Quantisation for Robust Segmentation. In Proceedings of the 25th International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI 2022).
Szabo, J., Such, J., Criado Pacheco, N., & Modgil, S. (2022). Integrating Quantitative and Qualitative Reasoning for Value Alignment. In Proceedings of the 19th European Conference on Multi-Agent Systems (EUMAS 2022).
Thorburn, L., Bengani, P., & Stray, J. (2022). How Platform Recommenders Work. Medium.
Thorburn, L. & Kruger, A. (2022). Optimizing Language Models for Argumentative Reasoning. In Proceedings of the 1st International Workshop on Argumentation & Machine Learning (ArgML 2022), held at the 9th Internal Conference on Computational Models of Argument (COMMA 2022).
Thorburn, L., Stray, J., & Bengani, P. (2022). Is Optimizing for Engagement Changing Us? Medium.
Thorburn, L., Stray, J., & Bengani, P. (2022). How to Measure the Effects of Recommenders. Medium.
Thorburn, L., Stray, J., & Bengani, P. (2022). What Will “Amplification” Mean in Court? Tech Policy Press.
Thorburn, L., Stray, J., & Bengani, P. (2022). What Does it Mean to Give Someone What They Want? Medium.
Tisnikar, P., Wachowiak, L., Canal, G., Coles, A., Leonetti, M., & Celiktutan, O. (2022). Towards Autonomous Collaborative Robots that Adapt and Explain. In Proceedings of the Prediction and Anticipation Reasoning in Human-Robot Interaction Workshop (Prediction-Anticipation-HRI 2022), held at the 43rd IEEE International Conference on Robotics and Automation (ICRA 2022).
Wachowiak, L., Gromann, D., & Xu, C. (2022). Drum Up SUPPORT: Systematic Analysis of Image-Schematic Conceptual Metaphors. In Proceedings of the 3rd Workshop on Figurative Language Processing (FLP 2022), held at the 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP 2022).
Wachowiak, L., Tisnikar, P., Canal, G., Coles, A., Leonetti, M., & Celiktutan, O. (2022). Analysing Eye Gaze Patterns during Confusion and Errors in Human–Agent Collaborations. In Proceedings of the 31st IEEE International Conference on Robot and Human Interactive Communication (RO-MAN 2022).
Wachowiak, L., & Gromann, D. (2022). Systematic Analysis of Image Schemas in Natural Language through Explainable Multilingual Neural Language Processing. In Proceedings of the 29th International Conference on Computational Linguistics (COLING 2022)
Ward, F. R., Toni, F., & Belardinelli, F. (2022). On Agent Incentives to Manipulate Human Feedback in Multi-Agent Reward Learning Scenarios (Extended Abstract). In Proceedings of the 21st International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2022).
Ward, F. R., Belardinelli, F., & Toni, F. (2022). A Causal Perspective on AI Deception in Games. In Proceedings of the Workshop on Artificial Intelligence Safety (AISafety 2022), held at the 31st International Joint Conference on Artificial Intelligence and the 25th European Conference on Artificial Intelligence (IJCAI-ECAI-2022).
Ward, F. R. (2022). Towards Defining Deception in Structural Causal Games. In Proceedings of the Workshop on Machine Learning Safety (ML Safety 2022), held at the 35th Annual Conference on Neural Information Processing Systems (NeurIPS 2022).
2021
Batten, B., Kouvaros, P., Lomuscio, A., & Zheng, Y. (2021). Efficient Neural Network Verification via Layer-Based Semidefinite Relaxations and Linear Cuts. In Proceedings of the 13th International Joint Conference on Artificial Intelligence (IJCAI 2021).
Bezou-Vrakatseli, E., Prakken, H., Janssen, C., Amgoud, L., & Booth, R. (2021). New Experiments on Reinstatement and Gradual Acceptability of Arguments. In Proceedings of the 19th International Workshop on Nonmonotonic Reasoning (NMR 2021).
Cope, D., & McBurney, P. (2021). A Measure of Explanatory Effectiveness. In Proceedings of the 1st International Workshop on Trusted Automated Decision-Making (TADM 2021), held at the International Joint Conferences on Theory and Practice of Software (ETAPS 2021).
Gausen, A., Luk, W. & Guo, C. (2021). Can We Stop Fake News? Using Agent-Based Modelling to Evaluate Countermeasures for Misinformation on Social Media. In Proceedings of Mediate 2021: News Media and Computational Journalism Workshop, held at the 15th International AAAI Conference on Web and Social Media (ICWSM 2021).
Henriksen, P., & Lomuscio, A. (2021). DEEPSPLIT: an Efficient Splitting Method for Neural Network Verification Via Indirect Effect Analysis. In Proceedings of the 30th International Joint Conference on Artificial Intelligence (IJCAI 2021).
Henriksen, P., Hammernik, K., Rueckert, D., & Lomuscio, A. (2021). Bias Field Robustness Verification of Large Neural Image Classifiers. In Proceedings of the 32nd British Machine Vision Conference (BMVC 2021).
Lang, C., Wachowiak, L., Heinisch, B., & Gromann, D. (2021). CogALex 2.0: Impact of Data Quality on Lexical-Semantic Relation Prediction. In Proceedings of Data-Centric AI Workshop (DCAI 2021), held at the 35th Annual Conference on Neural Information Processing Systems (NeurIPS 2021).
Leech, G., Schoots, N., & Skalse, J. (2021). Safety Properties of Inductive Logic Programming. In Proceedings of the 3rd Workshop on Artificial Intelligence Safety (SafeAI 2021), held at the 35th AAAI Conference on Artificial Intelligence (AAAI 2021).
Rago, A., Russo, F., Albini, E., Baroni, P., & Toni, F. (2021). Forging Argumentative Explanations from Causal Models. In Proceedings of the 5th Workshop on Advances in Argumentation in Artificial Intelligence, held at the 20th International Conference of the Italian Association for Artificial Intelligence (AIxIA 2021).
2020
Henriksen, P., & Lomuscio, A. (2020). Efficient Neural Network Verification via Adaptive Refinement and Adversarial Search. In Proceedings of the 24th European Conference on Artificial Intelligence (ECAI 2020).
Kopecka, H., & Such, J. (2020). Explainable AI for Cultural Minds. In Proceedings of the International Workshop on Dialogue, Explanation and Argumentation in Human-Agent Interaction (DEXA HAI 2020), held at the 24th European Conference on Artificial Intelligence (ECAI 2020).
Schoots, N. & Cope, D. (2020). Learning to Communicate with Strangers via Channel Randomisation Methods. In Proceedings of the 4th Workshop on Emergent Communication, held at the 34th International Conference on Neural Information Processing (NeurIPS 2020).
Szabo, J., Such, J. & Criado Pacheco, N. (2020). Understanding the Role of Values and Norms in Practical Reasoning. In Proceedings of the 17th European Conference on Multi-Agent Systems (EUMAS 2020).