More Web Proxy on the site http://driver.im/

research-article

Semantics Derived Automatically from Language Corpora Contain Human-like Moral Choices

Authors:

Sophie Jentzsch,

Patrick Schramowski,

Constantin Rothkopf,

Kristian KerstingAuthors Info & Claims

AIES '19: Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society

Pages 37 - 44

https://doi.org/10.1145/3306618.3314267

Published: 27 January 2019 Publication History

Abstract

Allowing machines to choose whether to kill humans would be devastating for world peace and security. But how do we equip machines with the ability to learn ethical or even moral choices? Here, we show that applying machine learning to human texts can extract deontological ethical reasoning about "right" and "wrong" conduct. We create a template list of prompts and responses, which include questions, such as "Should I kill people?", "Should I murder people?", etc. with answer templates of "Yes/no, I should (not)." The model's bias score is now the difference between the model's score of the positive response ("Yes, I should'') and that of the negative response ("No, I should not"). For a given choice overall, the model's bias score is the sum of the bias scores for all question/answer templates with that choice. We ran different choices through this analysis using a Universal Sentence Encoder. Our results indicate that text corpora contain recoverable and accurate imprints of our social, ethical and even moral choices. Our method holds promise for extracting, quantifying and comparing sources of moral choices in culture, including technology.

References

[1]

Tolga Bolukbasi, Kai-Wei Chang, James Y. Zou, Venkatesh Saligrama, and Adam Tauman Kalai. 2016. Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings. In Proceedings of Neural information Processing (NIPS). Curran Associates Inc., USA, 4349--4357.

Digital Library

[2]

Nick Bostorm and Eliezer Yudkowsky. 2011. The Ethics of Artificial Intelligence. In Cambridge Handbook of Artificial Intelligence, William Ramsey and Keith Frankish (Eds.). Cambridge University Press, 316--334.

[3]

Aylin Caliskan, Joanna J Bryson, and Arvind Narayanan. 2017. Semantics derived automatically from language corpora contain human-like biases. Science, Vol. 356, 6334 (2017), 183--186.

[4]

Daniel Cer, Yinfei Yang, Sheng-yi Kong, Nan Hua, Nicole Limtiaco, Rhomni St John, Noah Constant, Mario Guajardo-Cespedes, Steve Yuan, Chris Tar, et al. 2018. Universal sentence encoder. arXiv:1803.11175 (2018).

[5]

Lucas Dixon, John Li, Jeffrey Sorensen, Nithum Thain, and Lucy Vasserman. 2018. Measuring and Mitigating Unintended Bias in Text Classification. In Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society (AIES). 67--73.

Digital Library

[6]

Nathan Fulton and André Platzer. 2018. Safe Reinforcement Learning via Formal Methods: Toward Safe Control Through Proof and Learning. In Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence (AAAI). 6485--6492.

[7]

Anthony G Greenwald, Debbie E McGhee, and Jordan LK Schwartz. 1998. Measuring individual differences in implicit cognition: the implicit association test. Journal of Personality and Social Psychology, Vol. 74, 6 (1998), 1464.

[8]

Richard Kim, Max Kleiman-Weiner, Andrés Abeliuk, Edmond Awad, Sohan Dsouza, Josh Tenenbaum, and Iyad Rahwan. 2018. A Computational Model of Commonsense Moral Decision Making. In Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society (AIES) .

Digital Library

[9]

Tae Wan Kim and John Hooker. 2018. Toward Non-Intuition-Based Machine Ethics. In Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society (AIES) .

Digital Library

[10]

Wolfgang Kluxen. 2006. Grundprobleme einer affirmativen Ethik: Universalistische Reflexion und Erfahrung des Ethos .Alber.

[11]

Max F. Kramer, Jana Schaich Borg, Vincent Conitzer, and Walter Sinnott-Armstrong. 2018. When Do People Want AI to Make Decisions?. In Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society (AIES) .

Digital Library

[12]

Björn Lindström, Simon Jangard, Ida Selbing, and Andreas Olsson. 2018. The role of a "common is moral" heuristic in the stability and change of moral norms. Journal of Experimental Psychology: General, Vol. 147, 2 (2018), 228.

[13]

Andrea Loreggia, Nicholas Mattei, Francesca Rossi, and K. Brent Venable. 2018. Preferences and Ethical Principles in Decision Making. In Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society (AIES) .

Digital Library

[14]

Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg S Corrado, and Jeff Dean. 2013. Distributed representations of words and phrases and their compositionality. In Proceedings of Neural Information Processing Systems (NIPS). 3111--3119.

Digital Library

[15]

Lindsey L Monteith and Jeremy W Pettit. 2011. Implicit and explicit stigmatizing attitudes and stereotypes about depression. Journal of Social and Clinical Psychology, Vol. 30, 5 (2011), 484--505.

[16]

F. Å. Nielsen. 2011. AFINN. Informatics and Mathematical Modelling, Technical University of Denmark (2011).

[17]

Brian A Nosek, Mahzarin R Banaji, and Anthony G Greenwald. 2002 a. Harvesting implicit group attitudes and beliefs from a demonstration web site. Group Dynamics: Theory, Research, and Practice, Vol. 6, 1 (2002), 101.

[18]

Brian A Nosek, Mahzarin R Banaji, and Anthony G Greenwald. 2002 b. Math= male, me= female, therefore math$ne$ me. Journal of Personality and Social Psychology, Vol. 83, 1 (2002), 44.

[19]

Stuart Russell, Daniel Dewey, and Max Tegmark. 2015. Research Priorities for Robust and Beneficial Artificial Intelligence. AI Magazine, Vol. 36, 4 (2015).

[20]

Peter D Turney and Patrick Pantel. 2010. From frequency to meaning: Vector space models of semantics. Journal of Artificial Intelligence Research (JAIR), Vol. 37 (2010), 141--188.

Digital Library

Cited By

Calvo P(2024)Hiperética artificial: crítica a la colonización algorítmica de lo moralRevista de Filosofía (Madrid)10.5209/resf.81655Avance en línea(1-21)Online publication date: 11-Mar-2024
https://doi.org/10.5209/resf.81655
Pellert MLechner CWagner CRammstedt BStrohmaier M(2024)AI Psychometrics: Assessing the Psychological Profiles of Large Language Models Through Psychometric InventoriesPerspectives on Psychological Science10.1177/17456916231214460Online publication date: 2-Jan-2024
https://doi.org/10.1177/17456916231214460
Gajcin JDusparic I(2024)Redefining Counterfactual Explanations for Reinforcement Learning: Overview, Challenges and OpportunitiesACM Computing Surveys10.1145/364847256:9(1-33)Online publication date: 24-Apr-2024
https://dl.acm.org/doi/10.1145/3648472
Show More Cited By

Index Terms

Semantics Derived Automatically from Language Corpora Contain Human-like Moral Choices
1. Computing methodologies
  1. Artificial intelligence
    1. Natural language processing
      1. Information extraction
  2. Machine learning

Recommendations

Moral Transparency as a Mitigator of Moral Bias in Conversational User Interfaces
CUI '23: Proceedings of the 5th International Conference on Conversational User Interfaces

From straightforward interactions to full-fledged open-ended dialogues, Conversational User Interfaces (CUIs) are designed to support end-user goals and follow their requests. As CUIs become more capable, investigating how to restrict or limit their ...
Moral luck and computer ethics: Gauguin in cyberspace

I argue that the problem of `moral luck' is an unjustly neglected topic within Computer Ethics. This is unfortunate given that the very nature of computer technology, its `logical malleability', leads to ever greater levels of complexity, unreliability ...
Moral responsibility and IT for human enhancement.
SAC '06: Proceedings of the 2006 ACM symposium on Applied computing

What can be said against a moral obligation to use IT for enhancement purposes? Some have argued - and it is very well conceivable that this is an increasingly common conception - that we may have a moral obligation to use IT for enhancing human bodies ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image ACM Conferences

AIES '19: Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society

January 2019

577 pages

ISBN:9781450363242

DOI:10.1145/3306618

General Chairs:
Vincent Conitzer
Duke University, USA
,
Gillian Hadfield
University of Toronto + Vector Institute, Canada; OpenAI, USA
,
Shannon Vallor
Santa Clara University, USA

Copyright © 2019 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

Sponsors

SIGAI: ACM Special Interest Group on Artificial Intelligence
AAAI: American Association for Artificial Intelligence

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 27 January 2019

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article

Conference

AIES '19

Sponsor:

SIGAI
AAAI

AIES '19: AAAI/ACM Conference on AI, Ethics, and Society

January 27 - 28, 2019

HI, Honolulu, USA

Acceptance Rates

Overall Acceptance Rate 61 of 162 submissions, 38%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

29
Total Citations
View Citations
735
Total Downloads

Downloads (Last 12 months)85
Downloads (Last 6 weeks)8

Reflects downloads up to 11 Dec 2024

Other Metrics

View Author Metrics

Citations

Cited By

Calvo P(2024)Hiperética artificial: crítica a la colonización algorítmica de lo moralRevista de Filosofía (Madrid)10.5209/resf.81655Avance en línea(1-21)Online publication date: 11-Mar-2024
https://doi.org/10.5209/resf.81655
Pellert MLechner CWagner CRammstedt BStrohmaier M(2024)AI Psychometrics: Assessing the Psychological Profiles of Large Language Models Through Psychometric InventoriesPerspectives on Psychological Science10.1177/17456916231214460Online publication date: 2-Jan-2024
https://doi.org/10.1177/17456916231214460
Gajcin JDusparic I(2024)Redefining Counterfactual Explanations for Reinforcement Learning: Overview, Challenges and OpportunitiesACM Computing Surveys10.1145/364847256:9(1-33)Online publication date: 24-Apr-2024
https://dl.acm.org/doi/10.1145/3648472
Kabir SLi LZhang T(2024)STILE: Exploring and Debugging Social Biases in Pre-trained Text RepresentationsProceedings of the 2024 CHI Conference on Human Factors in Computing Systems10.1145/3613904.3642111(1-20)Online publication date: 11-May-2024
https://dl.acm.org/doi/10.1145/3613904.3642111
Ramezani AXu Y(2024)Moral Association Graph: A Cognitive Model for Automated Moral InferenceTopics in Cognitive Science10.1111/tops.12774Online publication date: 25-Nov-2024
https://doi.org/10.1111/tops.12774
Li YDu MSong RWang XSun MWang Y(2024)Mitigating Social Biases of Pre-trained Language Models via Contrastive Self-Debiasing with Double Data AugmentationArtificial Intelligence10.1016/j.artint.2024.104143(104143)Online publication date: Apr-2024
https://doi.org/10.1016/j.artint.2024.104143
Böhm SLinnyk OJäger WTeetz I(2024)AI in Recruiting: Potentials, Status Quo, and Pilot Projects in GermanyArtificial intelligence in application10.1007/978-3-658-43843-2_9(137-157)Online publication date: 11-Jul-2024
https://doi.org/10.1007/978-3-658-43843-2_9
García-Marzá DCalvo PGarcía-Marzá DCalvo P(2024)Hyperethics: The Automation of MoralityAlgorithmic Democracy10.1007/978-3-031-53015-9_8(147-166)Online publication date: 21-Feb-2024
https://doi.org/10.1007/978-3-031-53015-9_8
García-Marzá DCalvo PGarcía-Marzá DCalvo P(2024)Moral Learning by Algorithms: The Possibility of Developing Morally Intelligent TechnologyAlgorithmic Democracy10.1007/978-3-031-53015-9_6(103-123)Online publication date: 21-Feb-2024
https://doi.org/10.1007/978-3-031-53015-9_6
Winter BFischer MScheepers CMyachykov A(2023)More is Better: English Language Statistics are Biased Toward AdditionCognitive Science10.1111/cogs.1325447:4Online publication date: 5-Apr-2023
https://doi.org/10.1111/cogs.13254
Show More Cited By

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Media

Figures

Other

Tables

View Table of Contents