Philosophical Specification of Empathetic Ethical Artificial Intelligence
Open accessThe DOI matches its Crossref record; 27 of the 29 references it cites were found in a registry or an index.
Abstract
In order to construct an ethical artificial intelligence (AI) two complex problems must be overcome. First, humans do not consistently agree on what is or is not ethical. Second, contemporary AI and machine learning methods tend to be blunt instruments which either search for solutions within the bounds of predefined rules or mimic behavior. An ethical AI must be capable of inferring unspoken rules, interpreting nuance and context, possess and be able to infer intent, and explain not just its actions but its intent. Using enactivism, semiotics, perceptual symbol systems, and symbol emergence, we specify an agent that learns not just arbitrary relations between signs but their meaning in terms of the perceptual states of its sensorimotor system. Subsequently it can learn what is meant by a sentence and infer the intent of others in terms of its own experiences. It has malleable intent because the meaning of symbols changes as it learns, and its intent is represented symbolically as a goal. As such it may learn a concept of what is most likely to be considered ethical by the majority within a population of humans, which may then be used as a goal. The meaning of abstract symbols is expressed using perceptual symbols of raw, multimodal sensorimotor stimuli as the weakest (consistent with Ockham’s Razor) necessary and sufficient concept, an intensional definition learned from an ostensive definition, from which the extensional definition or category of all ethical decisions may be obtained. Because these abstract symbols are the same for both situation and response, the same symbol is used when either performing or observing an action. This is akin to mirror neurons in the human brain. Mirror symbols may allow the agent to empathize, because its own experiences are associated with the symbol, which is also associated with the observation of another agent experiencing something that symbol represents.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source says what the claim attributes to it.
In the citing paper
“The solutions they construct then facilitate encoding and decoding of signals interpretable by both agents [11].”
From Compression, The Fermi Paradox and Artificial Super-Intelligence (2022) · cites this paper as [11]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Barredo Arrieta, A., Díaz-Rodríguez, N., Del Ser, J., Bennetot, A., Tabik, S., Barbado, A., Garcia, S., Gil-Lopez, S., Molina, D., Benjamins, R., et al. (2020) · Information Fusion · doi:10.1016/j.inffus.2019.12.012 · Cited by 10,423
Barsalou, L. W. (1999) · Behavioral and Brain Sciences · doi:10.1017/s0140525x99002149 · Cited by 6,887
Stanford Encyclopedia of Philosophy
(2015) · Choice Reviews Online · doi:10.5860/choice.187763 · Cited by 5,309
Harnad, S. (1990) · Physica D: Nonlinear Phenomena · doi:10.1016/0167-2789(90)90087-6 · Cited by 4,235 · cited 2×
“How is a symbol connected to that which it signifies? This is the “Symbol Grounding Problem” [15], in which Harnad declared pursuit of artificial cognition from a top-down perspective “hopelessly modular,” “parasitic on the meanings in the head of the interpreter” and above all inflexible in the sense that no behavior…”
BackgroundEmpathy and Moral Development: Implications for Caring and Justice
Hoffman, M. L. (2000) · Cambridge University Press eBooks · doi:10.1017/cbo9780511805851 · Cited by 2,788
Mind in life: biology, phenomenology, and the sciences of mind
(2008) · Choice Reviews Online · doi:10.5860/choice.45-2543 · Cited by 2,696 · cited 1×
“extracted from sensorimotor stimuli, what of the environment? It determines what actions may take place, what stimuli is generated and even stores information, does it not? This brings us to enactivism [16], in which the Cartesian”
BackgroundGPT-3: Its Nature, Scope, Limits, and Consequences
Floridi, L., & Chiriatti, M. (2020) · Minds and Machines · doi:10.1007/s11023-020-09548-1 · Cited by 2,519 · cited 10×
“GPT-3, the recent state of the art natural language model from OpenAI, can pull off some impressive tricks.”
BackgroundMethodInfluentialLewis, D. (1973) · The Journal of Philosophy · doi:10.2307/2025310 · Cited by 1,914
Stanford Encyclopedia of Philosophy
Wahlberg, L. (2017) · Lund University Publications (Lund University) · Cited by 1,854
The Book of Why: The New Science of Cause and Effect
Goldberg, L. R. (2019) · Notices of the American Mathematical Society · doi:10.1090/noti1912 · Cited by 1,655
Research works printed but not linked: 7
- Visser, 2019, Uber Not Criminally Liable After Self-Driving Car Killed Woman: Local Prosecutor: The Death of 49-Year-Old Elaine Herzberg Was the First Known Fatality Linked to a Autonomous Vehicle in the United States
- FitzPatrick, 2021, Morality and evolutionary biology
- Setiya, 2018, Intention
- Asimov, 1942, Runaround
- Gupta, 2019, Definitions
- Stueber, 2019, Empathy
- Ridge, 2019, Moral non-naturalism
Cited by
Khosravy, M., Gupta, N., Pasquali, A., Dey, N., Crespo, R. A. G., & Witkowski, O. (2023) · IEEE Transactions on Cognitive and Developmental Systems · doi:10.1109/tcds.2023.3326192 · Cited by 103
Symbol Emergence and the Solutions to Any Task
Bennett, M. T. (2022) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-93758-4_4 · Cited by 43
“Absent such tailoring and simplifying abstractions, a rationale of even moderate complexity may be uninterpretable [16,25].”
BackgroundMethodSelf-citationCustomer service with AI-powered human-robot collaboration (HRC): A literature review
Leocádio, D., Guedes, L., Oliveira, J., Reis, J., & Melão, N. (2024) · Procedia Computer Science · doi:10.1016/j.procs.2024.01.120 · Cited by 37
Compression, The Fermi Paradox and Artificial Super-Intelligence
Bennett, M. T. (2022) · Lecture notes in computer science · doi:10.1007/978-3-030-93758-4_5 · Cited by 31
Self-citationEmergent Causality and the Foundation of Consciousness
Bennett, M. T. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-33469-6_6 · Cited by 35
Self-citation
Metadata
- Authors
- Bennett, M. T., & Maruyama, Y.
- Affiliations
- Australian National University (AU)
- Venue
- IEEE Transactions on Cognitive and Developmental Systems
- Published
- 2022-06
- Volume
- 14
- Issue
- 2
- Pages
- 292-300
- ISSN
- 2379-8920 (ISSN-L)
- 2379-8939
- OpenAlex
- W3185285485
- Cited by
- 43
- References
- 29
- Citations by year
- 2026: 4 · 2025: 5 · 2024: 5 · 2023: 16 · 2022: 13
- FWCI
- 10.64
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE Transactions on Cognitive and Developmental Systems (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- ANU Open Research (Australian National University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Japan Science and Technology Agency (JPMJMS2033)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Ethics and Social Impacts of AI
- Physical Sciences › Computer Science › Artificial Intelligence › Psychiatry, Mental Health, Neuroscience
- Life Sciences › Neuroscience › Cognitive Neuroscience › Embodied and Extended Cognition
- Keywords
- ethical artificial intelligence, empathy, enactivism, semiotics, perceptual symbol systems, symbol emergence, intention inference, ostensive definition, mirror neurons, sensorimotor experience, ethical decision-making
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Philosophical Specification of Empathetic Ethical Artificial Intelligence. https://app.cochat.ai/papers/10.1109/tcds.2021.3099945
- The paper
- Bennett, M. T., & Maruyama, Y. (2022). Philosophical Specification of Empathetic Ethical Artificial Intelligence. IEEE Transactions on Cognitive and Developmental Systems. https://doi.org/10.1109/tcds.2021.3099945
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.