IS AI GROUND TRUTH REALLY TRUE? THE DANGERS OF TRAINING AND EVALUATING AI TOOLS BASED ON EXPERTS’ KNOW-WHAT.
The DOI matches its Crossref record; 64 of the 64 references it cites were found in a registry or an index.
Abstract
Organizational decision-makers need to evaluate AI tools in light of increasing claims that such tools outperform human experts. Yet, measuring the quality of knowledge work is challenging, raising the question of how to evaluate AI performance in such contexts. We investigate this question through a field study of a major U.S. hospital, observing how managers evaluated five different machine-learning (ML) based AI tools. Each tool reported high performance according to standard AI accuracy measures, which were based on ground truth labels provided by qualified experts. Trying these tools out in practice, however, revealed that none of them met expectations. Searching for explanations, managers began confronting the high uncertainty of experts’ know-what knowledge captured in ground truth labels used to train and validate ML models. In practice, experts address this uncertainty by drawing on rich know-how practices, which were not incorporated into these ML-based tools. Discovering the disconnect between AI’s know-what and experts’ know-how enabled managers to better understand the risks and benefits of each tool. This study shows dangers of treating ground truth labels used in ML models objectively when the underlying knowledge is uncertain. We outline implications of our study for developing, training, and evaluating AI for knowledge work.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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?
In the citing paper
“However, the literature emphasizes the need to diligently evaluate AI to avoid biases during AI operationalization (Lebovitz et al., 2021).”
From Artificial intelligence in innovation management: A review of innovation capabilities and a taxonomy of AI applications (2025) · cites this paper as Lebovitz et al., 2021
In the citing paper
“Using AI tools may have reduced some human error but could have introduced other errors into the human's judgment (e.g., due to biases or poor training data).”
From To Engage or Not to Engage with AI for Critical Judgments: How Professionals Deal with Opacity When Using AI for Medical Diagnosis (2022) · cites this paper as Lebovitz et al. 2021
In the citing paper
“Researchers have already raised issues of AI accuracy claims and 'superior to human' knowledge performance (Lebovitz et al. 2021).”
From To Engage or Not to Engage with AI for Critical Judgments: How Professionals Deal with Opacity When Using AI for Medical Diagnosis (2022) · cites this paper as Lebovitz et al. 2021
In the citing paper
“However, in many professional contexts, such evaluations are limited since the knowledge is highly uncertain and many 'ground truth' measures are based on knowledge claims that lack strong external validation (Lebovitz et al. 2021).”
From To Engage or Not to Engage with AI for Critical Judgments: How Professionals Deal with Opacity When Using AI for Medical Diagnosis (2022) · cites this paper as Lebovitz et al. 2021
In the citing paper
“For the purposes of a supervised training paradigm, data labels are considered the “ground truth” from which models are optimized [82].”
From Bias in medical AI: Implications for clinical decision-making (2024) · cites this paper as [82]
Citations
Cites
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333
Knowledge of the firm, combinative capabilities, and the replication of technology
Kogut, B., & Zander, U. (1992) · Organization Science · doi:10.1287/orsc.3.3.383 · Cited by 12,939
Arrieta, A. B., Díaz-Rodríguez, N., Del Ser, J., Bennetot, A., Tabik, S., Barbado, A., García, S., Gil-López, S., Molina, D., Benjamins, R., et al. (2019) · arXiv · doi:10.48550/arxiv.1910.10045 · Cited by 11,321
Hutchins, E. (1995) · doi:10.7551/mitpress/1881.001.0001 · Cited by 10,801
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
The future of employment: How susceptible are jobs to computerisation?
Frey, C. B., & Osborne, M. A. (2017) · Technological Forecasting and Social Change · doi:10.1016/j.techfore.2016.08.019 · Cited by 8,727
Brown, J. S., & Duguid, P. (1991) · Organization Science · doi:10.1287/orsc.2.1.40 · Cited by 8,390
Exploring internal stickiness: Impediments to the transfer of best practice within the firm
Szulanski, G. (1996) · Strategic Management Journal · doi:10.1002/smj.4250171105 · Cited by 7,839
The System of Professions: An Essay on the Division of Expert Labor
Abbott, A. (1988) · doi:10.7208/chicago/9780226189666.001.0001 · Cited by 7,733
Cognition in Practice: Mind, Mathematics and Culture in Everyday Life
Lave, J. (1988) · doi:10.1017/cbo9780511609268 · Cited by 5,148
Research works printed but not linked: 33
- Bechky, 2021, Blood, Powder, and Residue: How Crime Labs Translate Evidence into Proof
- Bechmann, 2019, Unsupervised by Any Other Name: Hidden Layers of Knowledge Production in Artificial Intelligence on Social Media, 6
- Berger, 1966, The Social Construction of Reality: A Treatise in the Sociology of Knowledge
- Bowker, 2000, Sorting Things Out: Classification and Its Consequences
- Chandrasekaran, 1980, RADEX– Towards a Computer-Based Radiology Consultant, 463
- Charmaz, 2014, Constructing Grounded Theory
- Dhar, 2016, When to Trust Robots with Decisions, and When Not To, Harvard Business Review
- Dreyfus, 2000, Mind Over Machine
- Garud, 1997, On the Distinction between Know-How, KnowWhat, and Know-Why, Advances in Strategic Management, 14, 81
- Glaser, 1967, Discovering Grounded Theory
- Langlotz, 2019, Will Artificial Intelligence Replace Radiologists?, Radiology: Artificial Intelligence, 1, e190058
- Latour, 1987, Science in Action: How to Follow Scientists and Engineers through Society
- Leonard-Barton, 1995, Wellsprings of Knowledge: Building and Sustaining the Sources of Innovation
- Mongan, 2020, Checklist for Artificial Intelligence in Medical Imaging (CLAIM): A Guide for Authors and Reviewers, Radiology: Artificial Intelligence, 2, e200029
- Nicolini, 2012, Practice Theory, Work, and Organization: An Introduction
- Oakden-Rayner, 2019, The Rebirth of CAD: How Is Modern AI Different from the CAD We Know?, Radiology: Artificial Intelligence, 1
- Pinch, 1987, The Social Construction of Facts and Artifacts: Or How the Sociology of Science and the Sociology of Technology Might Benefit Each Other, 17
- Polanyi, 1958, Personal Knowledge: Towards a Post-Critical Philosophy
- Polanyi, 1966, The Tacit Dimension
- Provost, 2013, Data Science for Business: What You Need to Know about Data Mining and Data-Analytic Thinking
- Rao, 2017, Sizing the Prize: What’s the Real Value of AI for Your Business and How Can You Capitalise
- Ryle, 1949, The Concept of Mind
- Schön, 1983, The Reflective Practitioner: How Professionals Think in Action
- Seamans, 2019, AI and the Economy, Innovation Policy and the Economy, 19, 161
- Shoham, 2018, The AI Index 2018 Annual Report
- Simon, 1987, Making Management Decisions: The Role of Intuition and Emotion, The Academy of Management Executive (1987-1989), 1, 57
- Smyth, 1994, Inferring Ground Truth from Subjective Labelling of Venus Images, Advances in Neural Information Processing Systems, 1085
- Spradley, 1979, The Ethnographic Interview
- Star, 1995, Ecologies of Knowledge: Work and Politics in Science and Technology
- Suchman, 1987, Plans and Situated Actions
- Timmermans, 2003, The Gold Standard: The Challenge of Evidence-Based Medicine
- Van Maanen, 1998, Qualitative Studies of Organizations
- von Hippel, 1988, The Sources of Innovation
Cited by
Dell’Acqua, F., McFowland, E., Mollick, E., Lifshitz, H., Kellogg, K. C., Rajendran, S., Krayer, L., Candelon, F., & Lakhani, K. R. (2026) · Organization Science · doi:10.1287/orsc.2025.21838 · Cited by 1,189
Self-citationManaging artificial intelligence
Berente, N., Gu, B., Recker, J., & Santhanam, R. (2021) · MIS Quarterly · doi:10.25300/misq/2021/16274 · Cited by 898
Dell'Acqua, F., McFowland III, E., Mollick, E. R., Lifshitz-Assaf, H., Kellogg, K., Rajendran, S., Krayer, L., Candelon, F., & Lakhani, K. R. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4573321 · Cited by 794
Self-citationWhen and How Artificial Intelligence Augments Employee Creativity
Jia, N., Luo, X., Fang, Z., & Liao, C. (2024) · Academy of Management Journal · doi:10.5465/amj.2022.0426 · Cited by 768
Lebovitz, S., Lifshitz-Assaf, H., & Levina, N. (2022) · Organization Science · doi:10.1287/orsc.2021.1549 · Cited by 632
Self-citation
Metadata
- Authors
- Lebovitz, S., Levina, N., & Lifshitz-Assaf, H.
- Affiliations
- University of Virginia (US)
- New York University (US)
- New York University, Stern School of Business, New York, NY 10003 U.S.A.
- Venue
- MIS Quarterly
- Publisher
- MIS Quarterly
- Published
- 2021-09-01
- Volume
- 45
- Issue
- 3
- Pages
- 1501-1526
- ISSN
- 0276-7783 (ISSN-L)
- 2162-9730
- OpenAlex
- W3168956186
- Cited by
- 49
- References
- 59
- Citations by year
- 2026: 3 · 2025: 11 · 2024: 16 · 2023: 14 · 2022: 3 · 2021: 1
- FWCI
- 3.01
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- MIS Quarterly (publishedVersion)
- Warwick Research Archive Portal (University of Warwick) (acceptedVersion)
- Journal of the Association for Information Systems (submittedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Artificial Intelligence Applications
- Social Sciences › Business, Management and Accounting › Management Information Systems › Information Systems Theories and Implementation
- Physical Sciences › Computer Science › Artificial Intelligence › Ethics and Social Impacts of AI
- Keywords
- AI evaluation, ground truth labels, expert knowledge, know-how, knowledge work, machine learning, hospital management, uncertainty, risks of AI adoption, human-AI comparison, organizational 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: IS AI GROUND TRUTH REALLY TRUE? THE DANGERS OF TRAINING AND EVALUATING AI TOOLS BASED ON EXPERTS’ KNOW-WHAT. https://app.cochat.ai/papers/10.25300/misq/2021/16564
- The paper
- Lebovitz, S., Levina, N., & Lifshitz-Assaf, H. (2021). IS AI GROUND TRUTH REALLY TRUE? THE DANGERS OF TRAINING AND EVALUATING AI TOOLS BASED ON EXPERTS’ KNOW-WHAT. MIS Quarterly. https://doi.org/10.25300/misq/2021/16564
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.