Experiences with Improving the Transparency of AI Models and Services
Open accessAbstract
AI models and services are used in a growing number of high-stakes areas, resulting in a need for increased transparency. Consistent with this, several proposals for higher quality and more consistent documentation of AI data, models, and systems have emerged. Little is known, however, about the needs of those who would produce or consume these new forms of documentation. Through semi-structured developer interviews, and two document-creation exercises, we have assembled a clearer picture of these needs and the various challenges faced in creating accurate and useful AI documentation. Based on the observations from this work, supplemented by feedback received during multiple design explorations and stakeholder conversations, we make recommendations for easing the collection and flexible presentation of AI facts to promote transparency.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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?
AI documentation is advocated to increase the transparency and facilitate understanding of AI, and is embodied in recently proposed features of AI Factsheets and Model Cards.
“AI documentation is advocated to increase the transparency and facilitate understanding of AI [35,36,40,75,76,82], and is embodied in recently proposed features of AI Factsheets [8,81] and Model Cards [64].”
From Investigating Explainability of Generative AI for Code through Scenario-based Design (2022) · cites this paper as [35]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
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 · see citing works
Gebru, T., Morgenstern, J., Vecchione, B., Vaughan, J. W., Wallach, H., Daumé, H., & Crawford, K. (2018) · arXiv · doi:10.48550/arxiv.1803.09010 · Cited by 2,474
Gebru, T., Morgenstern, J., Vecchione, B., Vaughan, J. W., Wallach, H., III, H. D., & Crawford, K. (2021) · Communications of the ACM · doi:10.1145/3458723 · Cited by 2,469 · see citing works
FactSheets: Increasing trust in AI services through supplier's declarations of conformity
Arnold, M., Bellamy, R. K. E., Hind, M., Houde, S., Mehta, S., Mojsilović, A., Nair, R., Ramamurthy, K. N., Olteanu, A., Piorkowski, D., et al. (2019) · IBM Journal of Research and Development · doi:10.1147/jrd.2019.2942288 · Cited by 434 · see citing works
Self-citationThe relevance of software documentation, tools and technologies: a survey
Forward, A., & Lethbridge, T. C. (2002) · Proceedings of the 2002 ACM symposium on Document engineering · doi:10.1145/585058.585065 · Cited by 268 · see citing works
Flagged first, then by citations
Research works printed but not linked: 17
- Bellamy, R. K. E.; Dey, K.; Hind, M.; Hoffman, S. C.; Houde, S.; Kannan, K.; Lohia, P.; Martino, J.; Mehta, S.; Mojsilović, A.; Nagar, S.; Ramamurthy, K. N.; Richards, J.; Saha, D.; Sattigeri, P.; Singh, M.; Varshney, K. R.; and Zhang, Y. 2019. AI fairness 360: An extensible toolkit for detecting and mitigating algorithmic bias. IBM Journal of Research & Development 63(4/5).
- Bender, E. M., and Friedman, B. 2018. Data statements for natural language processing: Toward mitigating system bias and enabling better science. Transactions of the Association of Computational Linguis- tics. [Ensign et al. 2017] Ensign, D.; Friedler, S. A.; Neville, S.; Scheidegger, C.; and Venkatasubramanian, S. 2017. Run- away feedback loops in predictive policing. [
- Garousi, G.; Garousi, V.; Moussavi, M.; Ruhe, G.; and Smith, B. 2013. Evaluating usage and quality of technical software documentation: An empirical study. In Proceedings of the 17th International Conference on Evaluation and Assessment in Software Engineering, 24- 35. ACM.
- Holland, S.; Hosny, A.; Newman, S.; Joseph, J.; and Chmielinski, K. 2018. The dataset nutrition label: A framework to drive higher data quality standards. arXiv:1805.03677. [IEEE 2017] IEEE. 2017. P7006 -standard for personal data artificial intelligence (AI) agent. https://standards.ieee.org/project/7006.html. · arXiv
- Maalej, W.; Tiarks, R.; Roehm, T.; and Koschke, R. 2014. On the comprehension of program com- prehension. ACM Transactions on Software Engineering and Methodology (TOSEM) 23(4):31.
- McBurney, P. W., and McMillan, C. 2014. Automatic documentation generation via source code summarization of method context. In Proceedings of the 22nd International Conference on Program Comprehension, 279-290. ACM.
- Meng, M.; Stein- hardt, S.; and Schubert, A. 2018. Application programming interface documentation: What do software developers want? Journal of Technical Writing and Communication 48(3):295-330.
- Mitchell, M.; Wu, S.; Zaldivar, A.; Barnes, P.; Vasserman, L.; Hutchinson, B.; Spitzer, E.; Raji, I. D.; and Gebru, T. 2019. Model cards for model report- ing. In Proceedings of the ACM Conference on Fairness, Accountability, and Transparency. [New Jersey 2019] New Jersey. 2019. New Jersey account- ability act.
- Papineni, K.; Roukos, S.; Ward, T.; and Zhu, W.-J. 2002. BLEU: A method for automatic eval- uation of machine translation. Proceedings of the 40th An- nual Meeting of the Association for Computational Linguis- tics (ACL).
- Robillard, M. P., and Deline, R. 2011. A field study of API learning obstacles. Empirical Software Engineering 16(6):703-732.
- Robillard, M. P.; Marcus, A.; Treude, C.; Bavota, G.; Chaparro, O.; Ernst, N.; Gerosa, M. A.; God- frey, M.; Lanza, M.; Linares-Vásquez, M.; et al. 2017. On- demand developer documentation. In 2017 IEEE Interna- tional Conference on Software Maintenance and Evolution (ICSME), 479-483. IEEE.
- Sohan, S. M.; Anslow, C.; and Maurer, F. 2015. Spyrest: Automated restful API documentation using an http proxy server (n). In 2015 30th IEEE/ACM International Conference on Automated Soft- ware Engineering (ASE), 271-276. IEEE.
- Sohan, S.; Maurer, F.; Anslow, C.; and Robillard, M. P. 2017. A study of the effectiveness of usage examples in rest API documentation. In 2017 IEEE Sympo- sium on Visual Languages and Human-Centric Computing (VL/HCC), 53-61. IEEE.
- Strickland, E. 2019. Racial bias found in algorithms that determine health care for millions of pa- tients. IEEE Spectrum.
- Subramanian, S.; Inozemtseva, L.; and Holmes, R. 2014. Live API documentation. In Proceedings of the 36th International Conference on Software Engineering, 643-652. ACM.
- Uddin, G., and Robillard, M. P. 2015. How API documentation fails. IEEE Software 32(4):68-75.
- Zhang, S.; Zhang, C.; and Ernst, M. D. 2011. Automated documentation inference to explain failed tests. In 2011 26th IEEE/ACM Interna- tional Conference on Automated Software Engineering (ASE 2011), 63-72. IEEE.
Cited by
Sorted by citations
Investigating Explainability of Generative AI for Code through Scenario-based Design
Sun, J., Liao, Q. V., Muller, M., Agarwal, M., Houde, S., Talamadupula, K., & Weisz, J. D. (2022) · 27th International Conference on Intelligent User Interfaces · doi:10.1145/3490099.3511119 · Cited by 219 · see citing works
Self-citationDesigning for Responsible Trust in AI Systems: A Communication Perspective
Liao, Q. V., & Sundar, S. S. (2022) · 2022 ACM Conference on Fairness Accountability and Transparency · doi:10.1145/3531146.3533182 · Cited by 165 · see citing works
Z-Inspection <sup>®</sup> : A Process to Assess Trustworthy AI
Zicari, R. V., Brodersen, J., Brusseau, J., Dudder, B., Eichhorn, T., Ivanov, T., Kararigas, G., Kringen, P., McCullough, M., Moslein, F., et al. (2021) · IEEE Transactions on Technology and Society · doi:10.1109/tts.2021.3066209 · Cited by 134 · see citing works
Wan, Q., Hu, S., Zhang, Y., Wang, P., Wen, B., & Lu, Z. (2024) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3637361 · Cited by 88 · see citing works
- Authors
- Hind, M., Houde, S., Martino, J., Mojsilovic, A., Piorkowski, D., Richards, J., & Varshney, K. R.
- Affiliations
- IBM (United States) (US)
- IBM Research - Cambridge (United States) (US)
- IBM Research, Yorktown Heights, NY, USA
- Venue
- Extended Abstracts of the 2020 CHI Conference on Human Factors in Computing Systems
- Publisher
- ACM
- Published
- 2020-04-25
- Pages
- 1-8
- OpenAlex
- W2990286780
- Cited by
- 44
- References
- 5
- Citations by year
- 2026: 4 · 2025: 6 · 2024: 11 · 2023: 2 · 2022: 10 · 2021: 8 · 2020: 3
- FWCI
- 2.20
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Social Sciences › Safety Research › Ethics and Social Impacts of AI
- Physical Sciences › Computer Science › Information Systems › Software Engineering Techniques and Practices
- Keywords
- AI transparency, AI documentation, artificial intelligence models, artificial intelligence systems, developer interviews, document creation, stakeholder feedback
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
