Datasheets for Datasets help ML Engineers Notice and Understand Ethical Issues in Training Data
The DOI matches its Crossref record; 23 of the 23 references it cites were found in a registry or an index.
Abstract
The social computing community has demonstrated interest in the ethical issues sometimes produced by machine learning (ML) models, like violations of privacy, fairness, and accountability. This paper discovers what kinds of ethical considerations machine learning engineers recognize, how they build understanding, and what decisions they make when working with a real-world dataset. In particular, it illustrates ways in which Datasheets for Datasets, an accountability intervention designed to help engineers explore unfamiliar training data, scaffolds the process of issue discovery, understanding, and ethical decision-making. Participants were asked to review an intentionally ethically problematic dataset and asked to think aloud as they used it to solve a given ML problem. Out of 23 participants, 11 were given a Datasheet they could use while completing the task. Participants were ethically sensitive enough to identify concerns in the dataset; participants who had a Datasheet did open and refer to it; and those with Datasheets mentioned ethical issues during the think-aloud earlier and more often than than those without. The think-aloud protocol offered a grounded description of how participants recognized, understood, and made a decision about ethical problems in an unfamiliar dataset. The method used in this study can test other interventions that claim to encourage recognition, promote understanding, and support decision-making among technologists.
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
A Style-Based Generator Architecture for Generative Adversarial Networks
Karras, T., Laine, S., & Aila, T. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00453 · Cited by 11,714 · cited 1×
“I selected 171 images from the Flickr-Faces-HQ (FFHQ) dataset [33].”
MethodA Survey on Bias and Fairness in Machine Learning
Mehrabi, N., Morstatter, F., Saxena, N., Lerman, K., & Galstyan, A. (2019) · arXiv · doi:10.48550/arxiv.1908.09635 · Cited by 5,812
A Survey on Bias and Fairness in Machine Learning
Mehrabi, N., Morstatter, F., Saxena, N., Lerman, K., & Galstyan, A. (2022) · ACM Computing Surveys · doi:10.1145/3457607 · Cited by 5,812
Ethical Decision Making by Individuals in Organizations: An Issue-Contingent Model
Jones, T. M. (1991) · The Academy of Management Review · doi:10.2307/258867 · Cited by 4,135 · cited 1×
“This view of ES strikes a chord with long-standing research models that assert that ethical decision-making is dependent on the worker and their work characteristics [61] and influenced by the particulars of the ethical issue [31].”
BackgroundBarocas, S., & Selbst, A. D. (2014) · doi:10.2139/ssrn.2477899 · Cited by 3,048
Model Cards for Model Reporting
Mitchell, M., Wu, S., Zaldivar, A., Barnes, P., Vasserman, L., Hutchinson, B., Spitzer, E., Raji, I. D., & Gebru, T. (2019) · Proceedings of the Conference on Fairness, Accountability, and Transparency · doi:10.1145/3287560.3287596 · Cited by 2,681 · cited 2×
“[44] discuss several targets of particularization as goals for their document, including how the cards can help stakeholders identify what questions to ask of a model and evaluate its suitability for a given context.”
BackgroundMan 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 2×
“’s “Man is to Computer Programmer as Woman is to Homemaker?” [8], or both.”
BackgroundFairness definitions explained
Verma, S., & Rubin, J. (2018) · Proceedings of the International Workshop on Software Fairness · doi:10.1145/3194770.3194776 · Cited by 1,124 · cited 1×
“In the ML fairness literature and among people impacted by algorithms, there are a wide range of definitions of fairness that can be sophisticated, contextually-determined, and contradictory with one another [25, 53, 59, 64].”
BackgroundBender, E. M., & Friedman, B. (2018) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00041 · Cited by 854 · cited 11×
“Others take another approach: in their paper proposing Data Statements for Natural Language Processing, Bender & Friedman argue that their proposed context document may surface bias and other ethical problems without a question directly about ethics: “We propose here that foregrounding the characteristics of our datas…”
BackgroundInfluentialImproving Fairness in Machine Learning Systems: What Do Industry Practitioners Need?
Holstein, K., Wortman Vaughan, J., Daumé, H., Dudik, M., & Wallach, H. (2019) · Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3290605.3300830 · Cited by 777 · cited 1×
“[27, 24, 5]) and is described by industry practitioners as a key place to intervene to support fairness in ML [28].”
Background
Cited by
AI Art and its Impact on Artists
Jiang, H. H., Brown, L., Cheng, J., Khan, M., Gupta, A., Workman, D., Hanna, A., Flowers, J., & Gebru, T. (2023) · Proceedings of the 2023 AAAI/ACM Conference on AI, Ethics, and Society · doi:10.1145/3600211.3604681 · Cited by 265
What is Human-Centered about Human-Centered AI? A Map of the Research Landscape
Capel, T., & Brereton, M. (2023) · Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3544548.3580959 · Cited by 228
“…data or model cards, documentation of the data and who is represented within it, as well as how the model was made, assumptions that were made, how the model behaves in relation to diverse groups of people, and how well the model performs in relation to those groups [45, 55, 68, 105, 191, 222].”
BackgroundOperationalising ethics in artificial intelligence for healthcare: a framework for AI developers
Solanki, P., Grundy, J., & Hussain, W. (2023) · AI and Ethics · doi:10.1007/s43681-022-00195-z · Cited by 157
“All datasets should have accompanying documentation to enhance transparency and help ML engineers identify and understand issues in training data [104, 154, 164].”
BackgroundMethodSeeing Like a Toolkit: How Toolkits Envision the Work of AI Ethics
Wong, R. Y., Madaio, M. A., & Merrill, N. (2023) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3579621 · Cited by 135
Exploring How Machine Learning Practitioners (Try To) Use Fairness Toolkits
Deng, W. H., Nagireddy, M., Lee, M. S. A., Singh, J., Wu, Z. S., Holstein, K., & Zhu, H. (2022) · 2022 ACM Conference on Fairness Accountability and Transparency · doi:10.1145/3531146.3533113 · Cited by 99
Data Statements: From Technical Concept to Community Practice
McMillan-Major, A., Bender, E. M., & Friedman, B. (2024) · ACM Journal on Responsible Computing · doi:10.1145/3594737 · Cited by 21
“Data statements have been used in dataset cataloging eforts to explore the gaps in existing data collections [33], and recent work with datasheets points to documentation’s ability to support developers’ awareness of ethical issues in ML technology [4].”
MethodTan, M., Lee, H., Wang, D., & Subramonyam, H. (2024) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3637358 · Cited by 14
“Documentation frameworks help engineers understand ethical issues in training data [12] and provide important guidelines supporting accountability in data quality standards.”
Background
Metadata
- Authors
- Boyd, K. L.
- Venue
- Proceedings of the ACM on Human-Computer Interaction
- Published
- 2021-10-13
- Volume
- 5
- Issue
- CSCW2
- Pages
- 1-27
- ISSN
- 2573-0142 (ISSN-L)
- OpenAlex
- W3206271843
- Cited by
- 67
- References
- 23
- FWCI
- 14.21
- Type
- journal article
- 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
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.