A Computational Model of Commonsense Moral Decision Making

A Computational Model of Commonsense Moral Decision Making. Kim, R., Kleiman-Weiner, M., Abeliuk, A., Awad, E., Dsouza, S., Tenenbaum, J., & Rahwan, I. arXiv:1801.04346 [cs], January, 2018. arXiv: 1801.04346

Paper abstract bibtex

We introduce a new computational model of moral decision making, drawing on a recent theory of commonsense moral learning via social dynamics. Our model describes moral dilemmas as a utility function that computes trade-offs in values over abstract moral dimensions, which provide interpretable parameter values when implemented in machine-led ethical decision-making. Moreover, characterizing the social structures of individuals and groups as a hierarchical Bayesian model, we show that a useful description of an individual's moral values - as well as a group's shared values - can be inferred from a limited amount of observed data. Finally, we apply and evaluate our approach to data from the Moral Machine, a web application that collects human judgments on moral dilemmas involving autonomous vehicles.

@article{kim_computational_2018,
	title = {A {Computational} {Model} of {Commonsense} {Moral} {Decision} {Making}},
	url = {http://arxiv.org/abs/1801.04346},
	abstract = {We introduce a new computational model of moral decision making, drawing on a recent theory of commonsense moral learning via social dynamics. Our model describes moral dilemmas as a utility function that computes trade-offs in values over abstract moral dimensions, which provide interpretable parameter values when implemented in machine-led ethical decision-making. Moreover, characterizing the social structures of individuals and groups as a hierarchical Bayesian model, we show that a useful description of an individual's moral values - as well as a group's shared values - can be inferred from a limited amount of observed data. Finally, we apply and evaluate our approach to data from the Moral Machine, a web application that collects human judgments on moral dilemmas involving autonomous vehicles.},
	urldate = {2019-04-06},
	journal = {arXiv:1801.04346 [cs]},
	author = {Kim, Richard and Kleiman-Weiner, Max and Abeliuk, Andres and Awad, Edmond and Dsouza, Sohan and Tenenbaum, Josh and Rahwan, Iyad},
	month = jan,
	year = {2018},
	note = {arXiv: 1801.04346},
	keywords = {Computer Science - Artificial Intelligence},
}

Downloads: 0

{"_id":"ju5BT8NYPiSbZBQQw","bibbaseid":"kim-kleimanweiner-abeliuk-awad-dsouza-tenenbaum-rahwan-acomputationalmodelofcommonsensemoraldecisionmaking-2018","downloads":0,"creationDate":"2019-02-01T01:48:28.223Z","title":"A Computational Model of Commonsense Moral Decision Making","author_short":["Kim, R.","Kleiman-Weiner, M.","Abeliuk, A.","Awad, E.","Dsouza, S.","Tenenbaum, J.","Rahwan, I."],"year":2018,"bibtype":"article","biburl":"https://bibbase.org/zotero/henarcos","bibdata":{"bibtype":"article","type":"article","title":"A Computational Model of Commonsense Moral Decision Making","url":"http://arxiv.org/abs/1801.04346","abstract":"We introduce a new computational model of moral decision making, drawing on a recent theory of commonsense moral learning via social dynamics. Our model describes moral dilemmas as a utility function that computes trade-offs in values over abstract moral dimensions, which provide interpretable parameter values when implemented in machine-led ethical decision-making. Moreover, characterizing the social structures of individuals and groups as a hierarchical Bayesian model, we show that a useful description of an individual's moral values - as well as a group's shared values - can be inferred from a limited amount of observed data. Finally, we apply and evaluate our approach to data from the Moral Machine, a web application that collects human judgments on moral dilemmas involving autonomous vehicles.","urldate":"2019-04-06","journal":"arXiv:1801.04346 [cs]","author":[{"propositions":[],"lastnames":["Kim"],"firstnames":["Richard"],"suffixes":[]},{"propositions":[],"lastnames":["Kleiman-Weiner"],"firstnames":["Max"],"suffixes":[]},{"propositions":[],"lastnames":["Abeliuk"],"firstnames":["Andres"],"suffixes":[]},{"propositions":[],"lastnames":["Awad"],"firstnames":["Edmond"],"suffixes":[]},{"propositions":[],"lastnames":["Dsouza"],"firstnames":["Sohan"],"suffixes":[]},{"propositions":[],"lastnames":["Tenenbaum"],"firstnames":["Josh"],"suffixes":[]},{"propositions":[],"lastnames":["Rahwan"],"firstnames":["Iyad"],"suffixes":[]}],"month":"January","year":"2018","note":"arXiv: 1801.04346","keywords":"Computer Science - Artificial Intelligence","bibtex":"@article{kim_computational_2018,\n\ttitle = {A {Computational} {Model} of {Commonsense} {Moral} {Decision} {Making}},\n\turl = {http://arxiv.org/abs/1801.04346},\n\tabstract = {We introduce a new computational model of moral decision making, drawing on a recent theory of commonsense moral learning via social dynamics. Our model describes moral dilemmas as a utility function that computes trade-offs in values over abstract moral dimensions, which provide interpretable parameter values when implemented in machine-led ethical decision-making. Moreover, characterizing the social structures of individuals and groups as a hierarchical Bayesian model, we show that a useful description of an individual's moral values - as well as a group's shared values - can be inferred from a limited amount of observed data. Finally, we apply and evaluate our approach to data from the Moral Machine, a web application that collects human judgments on moral dilemmas involving autonomous vehicles.},\n\turldate = {2019-04-06},\n\tjournal = {arXiv:1801.04346 [cs]},\n\tauthor = {Kim, Richard and Kleiman-Weiner, Max and Abeliuk, Andres and Awad, Edmond and Dsouza, Sohan and Tenenbaum, Josh and Rahwan, Iyad},\n\tmonth = jan,\n\tyear = {2018},\n\tnote = {arXiv: 1801.04346},\n\tkeywords = {Computer Science - Artificial Intelligence},\n}\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n","author_short":["Kim, R.","Kleiman-Weiner, M.","Abeliuk, A.","Awad, E.","Dsouza, S.","Tenenbaum, J.","Rahwan, I."],"key":"kim_computational_2018","id":"kim_computational_2018","bibbaseid":"kim-kleimanweiner-abeliuk-awad-dsouza-tenenbaum-rahwan-acomputationalmodelofcommonsensemoraldecisionmaking-2018","role":"author","urls":{"Paper":"http://arxiv.org/abs/1801.04346"},"keyword":["Computer Science - Artificial Intelligence"],"metadata":{"authorlinks":{}},"downloads":0,"html":""},"search_terms":["computational","model","commonsense","moral","decision","making","kim","kleiman-weiner","abeliuk","awad","dsouza","tenenbaum","rahwan"],"keywords":["computer science - artificial intelligence"],"authorIDs":[],"dataSources":["qXmB8Cnrcvx883Fwx","efWerWm2QPDBjueMK","FSoKwX2WQoR9zQsgd","ea2By6aALWHHyh48d"]}