Guardado en:
Detalles Bibliográficos
Autores principales: Moore, Jared, Choi, Yejin, Levine, Sydney
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2410.05496
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913535939837952
author Moore, Jared
Choi, Yejin
Levine, Sydney
author_facet Moore, Jared
Choi, Yejin
Levine, Sydney
contents What is the best compromise in a situation where different people value different things? The most commonly accepted method for answering this question -- in fields across the behavioral and social sciences, decision theory, philosophy, and artificial intelligence development -- is simply to add up utilities associated with the different options and pick the solution with the largest sum. This ``utilitarian'' approach seems like the obvious, theory-neutral way of approaching the problem. But there is an important, though often-ignored, alternative: a ``contractualist'' approach, which advocates for an agreement-driven method of deciding. Remarkably, no research has presented empirical evidence directly comparing the intuitive plausibility of these two approaches. In this paper, we systematically explore the proposals suggested by each algorithm (the ``Utilitarian Sum'' and the contractualist ''Nash Product''), using a paradigm that applies those algorithms to aggregating preferences across groups in a social decision-making context. While the dominant approach to value aggregation up to now has been utilitarian, we find that people strongly prefer the aggregations recommended by the contractualist algorithm. Finally, we compare the judgments of large language models (LLMs) to that of our (human) participants, finding important misalignment between model and human preferences.
format Preprint
id arxiv_https___arxiv_org_abs_2410_05496
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Intuitions of Compromise: Utilitarianism vs. Contractualism
Moore, Jared
Choi, Yejin
Levine, Sydney
Artificial Intelligence
Computer Science and Game Theory
What is the best compromise in a situation where different people value different things? The most commonly accepted method for answering this question -- in fields across the behavioral and social sciences, decision theory, philosophy, and artificial intelligence development -- is simply to add up utilities associated with the different options and pick the solution with the largest sum. This ``utilitarian'' approach seems like the obvious, theory-neutral way of approaching the problem. But there is an important, though often-ignored, alternative: a ``contractualist'' approach, which advocates for an agreement-driven method of deciding. Remarkably, no research has presented empirical evidence directly comparing the intuitive plausibility of these two approaches. In this paper, we systematically explore the proposals suggested by each algorithm (the ``Utilitarian Sum'' and the contractualist ''Nash Product''), using a paradigm that applies those algorithms to aggregating preferences across groups in a social decision-making context. While the dominant approach to value aggregation up to now has been utilitarian, we find that people strongly prefer the aggregations recommended by the contractualist algorithm. Finally, we compare the judgments of large language models (LLMs) to that of our (human) participants, finding important misalignment between model and human preferences.
title Intuitions of Compromise: Utilitarianism vs. Contractualism
topic Artificial Intelligence
Computer Science and Game Theory
url https://arxiv.org/abs/2410.05496