Bio
Vanessa is a PhD student in the Causal Cognition Lab under the supervision of Prof. David Lagnado. Her research focuses on moral judgment and decision-making. In particular, she investigates causal explanations of moral responsibility. Some of her work explores how people use prior information about an agent (i.e., their moral character) when attributing blame in an unrelated situation; how people use causal and counterfactual reasoning when attributing responsibility, and how they distribute responsibility in complex situations where multiple agents interact and contribute to an outcome. Some of her other work involves exploring the metacognitive processes behind moral decision-making and how people learn from the outcomes of their previous moral decisions. In addition, she also investigate how people make judgments in legal contexts, for example, how inferences about a defendant’s character and mental states (such as their intentions, motives, and knowledge) can mitigate or exacerbate blame and influence how people reason about evidence.
Research interests
At the Alan Turing Institute, Vanessa is interested in extending her existing work on moral judgment and decision-making to applications for AI ethics. One application of this is to further her work on reinforcement learning to make AI moral decision-making safer and more beneficial. Another is to investigate how AI agents such as large language models make decisions in moral dilemmas, and in which ways these responses are similar or different to human responses – for example, whether they reflect the same biases in human moral decision-making.