Social choice ethics in artificial intelligence

By Seth D. Baum. 2017

118 citations recorded by the source corpus.

Subfields: Cognitive Neuroscience, Safety Research, Safety, Robustness & Interpretability

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cognitive Neuroscience

In Safety Research

In Safety, Robustness & Interpretability

Citations in the corpus

Scalable agent alignment via reward modeling: a research direction (2018, background): “How should the preferences of different users be aggregated and traded off against each other (Baum, 2017; Prasad, 2018)?”
Aligning AI Optimization to Community Well-Being (2020, background): “These challenges of collective action have been explored in the context of AI systems from the perspective of social choice theory (Baum 2020) and multi-stakeholder recommendation systems (Milano et al. 2019a).”
What to account for when accounting for algorithms: a systematic literature review on algorithmic accountability (2020, background): “Yet this does not entirely solve the problem, for as Baum [15] asks: whose considerations and norms and values are included in the design of the system and whose are left out?”
Conversational AI: Social and Ethical Considerations (2019, background): “Others argue for a Machine Ethics approach which involves encoding ethical standards and reasoning into the AI systems themselves [32] [3].”
How to Design AI for Social Good: Seven Essential Factors (2020, background): “Questions such as this are inevitably intertwined with wider ethical and political challenges regarding who has the power or “standing” to participate in this process of evaluation, as well as how multiple preferences are measured and aggregated, as Baum’s trichotomic framework outlines (Baum 2017).”
A Survey of Artificial General Intelligence Projects for Ethics, Risk, and Policy (2017, background): “; it describes “AI as a multiplier for human ingenuity” to solve problems like climate change and healthcare; and states “We believe that AI should ultimately belong to the world, in order to benefit the many and not the few”.96 Similarly, it writes AI will be “helping humanity tackle some of its gr”