| Recognising the importance of preference change: A call for a coordinated multidisciplinary research effort in the age of AI M Franklin, H Ashton, R Gorman, S Armstrong arXiv preprint arXiv:2203.10525, 2022 | 29 | 2022 |
| Definitions of intent suitable for algorithms H Ashton Artificial Intelligence and Law 31 (3), 515-546, 2023 | 25 | 2023 |
| The problem of behaviour and preference manipulation in AI systems H Ashton, M Franklin The AAAI-22 Workshop on Artificial Intelligence Safety (SafeAI 2022), 2022 | 25 | 2022 |
| Causal framework of artificial autonomous agent responsibility M Franklin, H Ashton, E Awad, D Lagnado Proceedings of the 2022 AAAI/ACM Conference on AI, Ethics, and Society, 276-284, 2022 | 22 | 2022 |
| Missing mechanisms of manipulation in the EU AI Act M Franklin, H Ashton, R Gorman, S Armstrong The International FLAIRS Conference Proceedings 35, 2022 | 21 | 2022 |
| Testing a definition of intent for AI in a legal setting H Ashton, M Franklin, D Lagnado Submitted manuscript, 2022 | 9 | 2022 |
| Beyond preferences in ai alignment T Zhi-Xuan, M Carroll, M Franklin, H Ashton Philosophical Studies, 1-51, 2024 | 8 | 2024 |
| Causal Campbell-Goodhart's law and Reinforcement Learning H Ashton arXiv preprint arXiv:2011.01010, 2020 | 8 | 2020 |
| Solutions to preference manipulation in recommender systems require knowledge of meta-preferences H Ashton, M Franklin arXiv preprint arXiv:2209.11801, 2022 | 6 | 2022 |
| Unpredictable robots elicit responsibility attributions. M Franklin, E Awad, H Ashton, D Lagnado Behavioral & Brain Sciences 46, 2023 | 5 | 2023 |
| Defining and Identifying the Legal Culpability of Side Effects Using Causal Graphs H Ashton CEUR Workshop Proceedings 3087, 2022 | 5 | 2022 |
| AI Legal Counsel to train and regulate legally constrained Autonomous systems H Ashton 2020 IEEE International Conference on Big Data (Big Data), 2093-2098, 2020 | 4 | 2020 |
| Definitions of intent for AI derived from common law H Ashton 14th International Workshop on Juris-informatics (JURISIN 2020). Available …, 2020 | 4 | 2020 |
| Preference Change in Persuasive Robotics M Franklin, H Ashton arXiv preprint arXiv:2206.10300, 2022 | 3 | 2022 |
| Extending counterfactual accounts of intent to include oblique intent H Ashton arXiv preprint arXiv:2106.03684, 2021 | 3 | 2021 |
| The corrupting influence of AI as a boss or counterparty H Ashton, M Franklin | 2 | 2022 |
| A method to check that participants really are imagining artificial minds when ascribing mental states H Ashton, M Franklin International Conference on Human-Computer Interaction, 470-474, 2022 | 2 | 2022 |
| What criminal and civil law tells us about Safe RL techniques to generate law-abiding behaviour. H Ashton SafeAI@ AAAI, 2021 | 2 | 2021 |
| Model-Free RL Agents Demonstrate System 1-Like Intentionality H Ashton, M Franklin arXiv preprint arXiv:2501.18299, 2025 | | 2025 |
| Concept Extrapolation: A Conceptual Primer M Franklin, R Gorman, H Ashton, S Armstrong arXiv preprint arXiv:2306.10999, 2023 | | 2023 |
