Toward Supporting Perceptual Complementarity in Human-AI Collaboration via Reflection on Unobservables
Open accessThe DOI matches its Crossref record; 28 of the 28 references it cites were found in a registry or an index.
Abstract
In many real world contexts, successful human-AI collaboration requires humans to productively integrate complementary sources of information into AI-informed decisions. However, in practice human decision-makers often lack understanding of what information an AI model has access to, in relation to themselves. There are few available guidelines regarding how to effectively communicate aboutunobservables: features that may influence the outcome, but which are unavailable to the model. In this work, we conducted an online experiment to understand whether and how explicitly communicating potentially relevant unobservables influences how people integrate model outputs and unobservables when making predictions. Our findings indicate that presenting prompts about unobservables can change how humans integrate model outputs and unobservables, but do not necessarily lead to improved performance. Furthermore, the impacts of these prompts can vary depending on decision-makers' prior domain expertise. We conclude by discussing implications for future research and design of AI-based decision support tools.
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
Trust in Automation: Designing for Appropriate Reliance
Lee, J. D., & See, K. A. (2004) · Human Factors: The Journal of the Human Factors and Ergonomics Society · doi:10.1518/hfes.46.1.50_30392 · Cited by 6,605 · cited 1×
“For instance, a long line of literature demonstrates that human decision-makers are often either too skeptical of useful AI outputs or too reliant upon erroneous or harmfully biased AI outputs [4, 14, 20, 31, 39].”
BackgroundAlgorithm aversion: People erroneously avoid algorithms after seeing them err.
Dietvorst, B. J., Simmons, J. P., & Massey, C. (2015) · Journal of Experimental Psychology: General · doi:10.1037/xge0000033 · Cited by 3,232
Building Machines That Learn and Think Like People
Lake, B. M., Ullman, T. D., Tenenbaum, J. B., & Gershman, S. J. (2016) · arXiv · doi:10.48550/arxiv.1604.00289 · Cited by 2,550
Human Decisions and Machine Predictions
Kleinberg, J., Lakkaraju, H., Leskovec, J., Ludwig, J., & Mullainathan, S. (2018) · The Quarterly Journal of Economics · doi:10.1093/qje/qjx032 · Cited by 1,040
Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance
Bansal, G., Wu, T., Zhou, J., Fok, R., Nushi, B., Kamar, E., Ribeiro, M. T., & Weld, D. (2021) · Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3411764.3445717 · Cited by 757 · cited 2×
“Several recent experimental studies have shown that, contrary to researchers’ intuitions, presenting in-the-moment explanations for an AI model’s prediction can often backfire, encouraging humans to over-rely on AI outputs even in the presence of large errors that they may otherwise have noticed [3, 39].”
MethodResultDoes the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance
Bansal, G., Wu, T., Zhou, J., Fok, R., Nushi, B., Kamar, E., Ribeiro, M. T., & Weld, D. S. (2020) · arXiv · doi:10.48550/arxiv.2006.14779 · Cited by 754
Manipulating and Measuring Model Interpretability
Poursabzi-Sangdeh, F., Goldstein, D. G., Hofman, J. M., Wortman Vaughan, J. W., & Wallach, H. (2021) · Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3411764.3445315 · Cited by 728 · cited 24×
“In many real-world settings where ADS are employed, humans use AI outputs as just one of several sources of information at their disposal to inform a decision [11, 23, 27].”
BackgroundMethodResultInfluentialManipulating and Measuring Model Interpretability
Poursabzi-Sangdeh, F., Goldstein, D. G., Hofman, J. M., Vaughan, J. W., & Wallach, H. (2018) · arXiv · doi:10.48550/arxiv.1802.07810 · Cited by 711
The Principles and Limits of Algorithm-in-the-Loop Decision Making
Green, B., & Chen, Y. (2019) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3359152 · Cited by 392 · cited 2×
“In other studies, human–AI collaboration has failed to improve or have even harmed decision quality [20, 39, 43].”
BackgroundDisparate Interactions: An Algorithm-in-the-Loop Analysis of Fairness in Risk Assessments
Green, B., & Chen, Y. (2019) · Proceedings of the Conference on Fairness, Accountability, and Transparency · doi:10.1145/3287560.3287563 · Cited by 275
Human–machine partnership with artificial intelligence for chest radiograph diagnosis
Patel, B. N., Rosenberg, L., Willcox, G., Baltaxe, D., Lyons, M., Irvin, J., Rajpurkar, P., Amrhein, T., Gupta, R., Halabi, S., et al. (2019) · npj Digital Medicine · doi:10.1038/s41746-019-0189-7 · Cited by 254
Yang, Q., Steinfeld, A., & Zimmerman, J. (2019) · Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3290605.3300468 · Cited by 247
A Case for Humans-in-the-Loop: Decisions in the Presence of Erroneous Algorithmic Scores
De-Arteaga, M., Fogliato, R., & Chouldechova, A. (2020) · Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3313831.3376638 · Cited by 221 · cited 9×
“Instead, call workers were more likely to avoid errors of omission, which correspond to false negative errors, by integrating other sources of information instead of relying on AI outputs alone [11].”
BackgroundMethodInfluentialSelf-citationWang, D., Wang, L., Zhang, Z., Wang, D., Zhu, H., Gao, Y., Fan, X., & Tian, F. (2021) · Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3411764.3445432 · Cited by 209 · cited 2×
“AI-based decision support tools (ADS) are being used to augment human decision-making across a growing range of domains—from predictive risk models used to augment decision-making in public services [11, 25, 27, 34, 41], to AI-based teacher support tools used in K-12 education [2, 7, 13, 23, 40], to clinical decision…”
BackgroundMethodA Conceptual Framework for Human–AI Hybrid Adaptivity in Education
Holstein, K., Aleven, V., & Rummel, N. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-52237-7_20 · Cited by 168 · cited 4×
“AI-based decision support tools (ADS) are being used to augment human decision-making across a growing range of domains—from predictive risk models used in public services [12, 26, 28, 37, 46], to AI-based teacher support tools used in K-12 education [2, 7, 14, 24, 45], to clinical decision support tools used in healt…”
BackgroundMethodInfluentialSelf-citationDesigning for human–AI complementarity in K‐12 education
Holstein, K., & Aleven, V. (2022) · AI Magazine · doi:10.1002/aaai.12058 · Cited by 156
Self-citationKawakami, A., Sivaraman, V., Cheng, H.-F., Stapleton, L., Cheng, Y., Qing, D., Perer, A., Wu, Z. S., Zhu, H., & Holstein, K. (2022) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3491102.3517439 · Cited by 143 · cited 10×
“A central dimension of human-AI complementarity is the often complementary nature of the information sources that the human and the AI model each have access to and are able to parse [12, 24, 28].”
BackgroundMethodInfluentialSelf-citationThe Selective Labels Problem: Evaluating Algorithmic Predictions in the Presence of Unobservables
Lakkaraju, H., Kleinberg, J., Leskovec, J., Ludwig, J., & Mullainathan, S. (2017) · Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/3097983.3098066 · Cited by 138
A Human-AI Collaborative Approach for Clinical Decision Making on Rehabilitation Assessment
Lee, M. H., Siewiorek, D. P., Smailagic, A., Bernardino, A., & Bermúdez i Badia, S. B. (2021) · Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3411764.3445472 · Cited by 137 · cited 3×
“AI-based decision support tools (ADS) are being used to augment human decision-making across a growing range of domains—from predictive risk models used to augment decision-making in public services [11, 25, 27, 34, 41], to AI-based teacher support tools used in K-12 education [2, 7, 13, 23, 40], to clinical decision…”
BackgroundMethodWilder, B., Horvitz, E., & Kamar, E. (2020) · Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2020/212 · Cited by 118
A Human-Centered Review of Algorithms used within the U.S. Child Welfare System
Saxena, D., Badillo-Urquiola, K., Wisniewski, P. J., & Guha, S. (2020) · Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3313831.3376229 · Cited by 116
Yang, Q., Zimmerman, J., Steinfeld, A., Carey, L., & Antaki, J. F. (2016) · Proceedings of the 2016 CHI Conference on Human Factors in Computing Systems · doi:10.1145/2858036.2858373 · Cited by 105
Shifting Concepts of Value: Designing Algorithmic Decision-Support Systems for Public Services
Holten Møller, N., Shklovski, I., & Hildebrandt, T. T. (2020) · Proceedings of the 11th Nordic Conference on Human-Computer Interaction: Shaping Experiences, Shaping Society · doi:10.1145/3419249.3420149 · Cited by 97
Predict Responsibly: Improving Fairness and Accuracy by Learning to Defer
Madras, D., Pitassi, T., & Zemel, R. (2017) · arXiv · doi:10.48550/arxiv.1711.06664 · Cited by 90
The TA Framework: Designing Real-time Teaching Augmentation for K-12 Classrooms
An, P., Holstein, K., d'Anjou, B., Eggen, B., & Bakker, S. (2020) · Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3313831.3376277 · Cited by 69 · cited 2×
“AI-based decision support tools (ADS) are being used to augment human decision-making across a growing range of domains—from predictive risk models used to augment decision-making in public services [11, 25, 27, 34, 41], to AI-based teacher support tools used in K-12 education [2, 7, 13, 23, 40], to clinical decision…”
BackgroundMethodSelf-citationYou’d Better Stop! Understanding Human Reliance on Machine Learning Models under Covariate Shift
Chiang, C.-W., & Yin, M. (2021) · 13th ACM Web Science Conference 2021 · doi:10.1145/3447535.3462487 · Cited by 53 · cited 4×
“, [6, 39]), participants had access only to this tabular information, and were not able to view images of the homes.”
BackgroundMethodInfluentialHuman-AI Collaboration with Bandit Feedback
Gao, R., Saar-Tsechansky, M., De-Arteaga, M., Han, L., Lee, M. K., & Lease, M. (2021) · arXiv · doi:10.48550/arxiv.2105.10614 · Cited by 23 · cited 1×
“, to ensure that AI systems handle the instances that are most difficult for humans and vice versa), [19, 39, 44, 51].”
BackgroundSelf-citationOn the Effect of Information Asymmetry in Human-AI Teams
Hemmer, P., Schemmer, M., Kühl, N., Vössing, M., & Satzger, G. (2022) · arXiv · doi:10.48550/arxiv.2205.01467 · Cited by 9
Cited by
Gomez, C., Cho, S. M., Ke, S., Huang, C.-M., & Unberath, M. (2025) · Frontiers in Computer Science · doi:10.3389/fcomp.2024.1521066 · Cited by 209
Enhancing AI-Assisted Group Decision Making through LLM-Powered Devil's Advocate
Chiang, C.-W., Lu, Z., Li, Z., & Yin, M. (2024) · Proceedings of the 29th International Conference on Intelligent User Interfaces · doi:10.1145/3640543.3645199 · Cited by 142
Human Delegation Behavior in Human-AI Collaboration: The Effect of Contextual Information
Spitzer, P., Holstein, J., Hemmer, P., Vössing, M., Kühl, N., Martin, D., & Satzger, G. (2025) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3710999 · Cited by 18
Metadata
- Authors
- Holstein, K., De-Arteaga, M., Tumati, L., & Cheng, Y.
- Venue
- Proceedings of the ACM on Human-Computer Interaction
- Published
- 2023-04-14
- Volume
- 7
- Issue
- CSCW1
- Pages
- 1-20
- ISSN
- 2573-0142 (ISSN-L)
- OpenAlex
- W4366004108
- Cited by
- 38
- References
- 28
- FWCI
- 10.70
- Type
- journal article
- Language
- en
- Open access
- hybrid
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.