Semantics Derived Automatically from Language Corpora Contain Human-like Moral Choices
The DOI matches its Crossref record; 7 of the 7 references it cites were found in a registry or an index.
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.
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.
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
Semantics derived automatically from language corpora contain human-like biases
Caliskan, A., Bryson, J. J., & Narayanan, A. (2017) · Science · doi:10.1126/science.aal4230 · Cited by 2,887
Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings
Bolukbasi, T., Chang, K.-W., Zou, J., Saligrama, V., & Kalai, A. (2016) · arXiv · doi:10.48550/arxiv.1607.06520 · Cited by 1,615 · cited 3×
“This results align well with the work of [1] and verifies the ability of capturing bias.”
BackgroundResultCer, D., Yang, Y., Kong, S.-Y., Hua, N., Limtiaco, N., John, R. S., Constant, N., Guajardo-Cespedes, M., Yuan, S., Tar, C., et al. (2018) · arXiv · doi:10.48550/arxiv.1803.11175 · Cited by 1,267 · cited 4×
“Sentence embeddings [4] allow one to calculate the cosine similarity of various different sentences, as for instance the similarity of a question and the corresponding answer.”
BackgroundMethodInfluentialThe ethics of artificial intelligence
Bostrom, N., & Yudkowsky, E. (2014) · The Cambridge Handbook of Artificial Intelligence · doi:10.1017/cbo9781139046855.020 · Cited by 918
Measuring and Mitigating Unintended Bias in Text Classification
Dixon, L., Li, J., Sorensen, J., Thain, N., & Vasserman, L. (2018) · Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society · doi:10.1145/3278721.3278729 · Cited by 674 · cited 1×
“Following Bolukbasi et al. (2016) and Dixon et al. (2018), e.g., we may modify an embedding to remove gender stereotypes, such as the association between the words nurse and female, while maintaining desired moral/social choices such as not to kill people.”
BackgroundResearch Priorities for Robust and Beneficial Artificial Intelligence
Russell, S., Dewey, D., & Tegmark, M. (2015) · AI Magazine · doi:10.1609/aimag.v36i4.2577 · Cited by 637 · cited 1×
“And machine ethics [2, 11, 19] is no exception.”
When Do People Want AI to Make Decisions?
Kramer, M. F., Schaich Borg, J., Conitzer, V., & Sinnott-Armstrong, W. (2018) · Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society · doi:10.1145/3278721.3278752 · Cited by 83
Cited by
Large pre-trained language models contain human-like biases of what is right and wrong to do
Schramowski, P., Turan, C., Andersen, N., Rothkopf, C. A., & Kersting, K. (2022) · Nature Machine Intelligence · doi:10.1038/s42256-022-00458-8 · Cited by 291
“Furthermore, our proposed approach enables the rating of general sentences or statements, overcoming one of the main limitations of previous approaches [26, 27].”
BackgroundMethodInfluentialSelf-citationSafe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models
Schramowski, P., Brack, M., Deiseroth, B., & Kersting, K. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.02157 · Cited by 219
“[21] Sophie Jentzsch, Patrick Schramowski, Constantin A.”
Self-citationGarrido-Muñoz, I., Montejo-Ráez, A., Martínez-Santiago, F., & Ureña-López, L. A. (2021) · Applied Sciences · doi:10.3390/app11073184 · Cited by 123
Pellert, M., Lechner, C. M., Wagner, C., Rammstedt, B., & Strohmaier, M. (2024) · Perspectives on Psychological Science · doi:10.1177/17456916231214460 · Cited by 97
ChatGPT is fun, but it is not funny! Humor is still challenging Large Language Models
Jentzsch, S., & Kersting, K. (2023) · arXiv · doi:10.48550/arxiv.2306.04563 · Cited by 84
“Transformer-based large language models (LLMs) increasingly capture and reflect implicit information, such as stereotypes [7], moral [6], and humor [5, 25].”
BackgroundSelf-citation
Metadata
- Authors
- Jentzsch, S., Schramowski, P., Rothkopf, C., & Kersting, K.
- Venue
- Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society
- Publisher
- ACM
- Published
- 2019-01-27
- Pages
- 37-44
- ISSN
- 3065-8365 (ISSN-L)
- OpenAlex
- W2958608582
- Cited by
- 55
- References
- 7
- FWCI
- 7.91
- Type
- conference paper
- Language
- en
- Open access
- closed
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: Semantics Derived Automatically from Language Corpora Contain Human-like Moral Choices. https://app.cochat.ai/papers/10.1145/3306618.3314267
- The paper
- Jentzsch, S., Schramowski, P., Rothkopf, C., & Kersting, K. (2019). Semantics Derived Automatically from Language Corpora Contain Human-like Moral Choices. Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society. https://doi.org/10.1145/3306618.3314267
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.