Vincent Valton | Searcharxiv

arXiv2023

Toward an Ethics of AI Belief

In this paper we, an epistemologist and a machine learning scientist, argue that we need to pursue a novel area of philosophical research in AI - the ethics of belief for AI. Here we take the ethics of belief to refer to a field at the intersection of epistemology and ethics concerned with possible moral, practical, and other non-truth-related dimensions of belief. In this paper we will primarily be concerned with the normative question within the ethics of belief regarding what agents - both human and artificial - ought to believe, rather than with questions concerning whether beliefs meet certain evaluative standards such as being true, being justified, constituting knowledge, etc. We suggest four topics in extant work in the ethics of (human) belief that can be applied to an ethics of AI belief: doxastic wronging by AI (morally wronging someone in virtue of beliefs held about them); morally owed beliefs (beliefs that agents are morally obligated to hold); pragmatic and moral encroachment (cases where the practical or moral features of a belief is relevant to its epistemic status, and in our case specifically to whether an agent ought to hold the belief); and moral responsibility for AI beliefs. We also indicate two relatively nascent areas of philosophical research that haven't yet been generally recognized as ethics of AI belief research, but that do fall within this field of research in virtue of investigating various moral and practical dimensions of belief: the epistemic and ethical decolonization of AI; and epistemic injustice in AI.

cs.CY↗

arXiv2020

Recommendations for Bayesian hierarchical model specifications for case-control studies in mental health

Hierarchical model fitting has become commonplace for case-control studies of cognition and behaviour in mental health. However, these techniques require us to formalise assumptions about the data-generating process at the group level, which may not be known. Specifically, researchers typically must choose whether to assume all subjects are drawn from a common population, or to model them as deriving from separate populations. These assumptions have profound implications for computational psychiatry, as they affect the resulting inference (latent parameter recovery) and may conflate or mask true group-level differences. To test these assumptions we ran systematic simulations on synthetic multi-group behavioural data from a commonly used multi-armed bandit task (reinforcement learning task). We then examined recovery of group differences in latent parameter space under the two commonly used generative modelling assumptions: (1) modelling groups under a common shared group-level prior (assuming all participants are generated from a common distribution, and are likely to share common characteristics); (2) modelling separate groups based on symptomatology or diagnostic labels, resulting in separate group-level priors. We evaluated the robustness of these approaches to variations in data quality and prior specifications on a variety of metrics. We found that fitting groups separately (assumptions 2), provided the most accurate and robust inference across all conditions. Our results suggest that when dealing with data from multiple clinical groups, researchers should analyse patient and control groups separately as it provides the most accurate and robust recovery of the parameters of interest.

cs.CY↗