Moral Uncertainty and the Problem of Fanaticism

Authors: Jazon Szabo, Natalia Criado, Jose Such, Sanjay Modgil

AAAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical this paper contributes to the field of moral uncertainty by 1) formalising the problem of fanaticism as a property of social welfare functionals and 2) providing non-fanatical alternatives to MEC... We prove that MEC is in fact maximally fanatical... We prove that neither novel weighted swfs are Pascalian and that Highest Median is not fanatical at all.
Researcher Affiliation Academia 1King s College London, UK 2VRAIN, Universitat Politecnica de Valencia, Spain
Pseudocode No The paper defines functions and computations like 'wam(F, a) = P t T c(t)t(a)' and 'se(F, a) = sort( t(a)|t T )', but it does not include structured pseudocode or algorithm blocks with formal labeling such as 'Algorithm 1' or 'Pseudocode'.
Open Source Code No The paper does not contain any statement about releasing source code, nor does it provide a link to a code repository.
Open Datasets No The paper provides a running example with illustrative numerical valuations (Table 1: 'Evaluations FROBO s ethical theories'), but this is for conceptual demonstration, not an empirical dataset. There is no mention of any publicly available or open dataset used for training or evaluation.
Dataset Splits No The paper presents theoretical formalizations and proofs. It does not describe any experimental procedures involving dataset splits for training, validation, or testing.
Hardware Specification No As a theoretical paper focusing on formal definitions and mathematical proofs, no specific hardware (like GPU models, CPU models, or cloud resources) is mentioned as being used for experiments.
Software Dependencies No The paper is theoretical and does not describe any implementation details that would require specific software dependencies with version numbers.
Experiment Setup No The paper focuses on theoretical formalizations and proofs, and therefore does not include details on experimental setup such as hyperparameter values, training configurations, or system-level settings.