On Human Predictions with Explanations and Predictions of Machine Learning Models: A Case Study on Deception Detection
Open accessThe DOI matches its Crossref record; 87 of the 87 references it cites were found in a registry or an index.
Abstract
Humans are the final decision makers in critical tasks that involve ethical and legal concerns, ranging from recidivism prediction, to medical diagnosis, to fighting against fake news. Although machine learning models can sometimes achieve impressive performance in these tasks, these tasks are not amenable to full automation. To realize the potential of machine learning for improving human decisions, it is important to understand how assistance from machine learning models affects human performance and human agency.
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.
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?
The cited source doesn’t support the claim as written.
In the citing paper
“this remedy is unlikely to be effective: substantial evidence demonstrates that humans tend to override algorithms in detrimental rather than beneficial ways”
From The flaws of policies requiring human oversight of government algorithms (2022) · cites this paper as Lai & Tan, 2019
Checked by a reasoning model — may be wrong.
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“They found that all these features increased people's trust, measured as acceptance of the AI's recommendation as the final decision, and also the decision accuracy.”
From Effect of confidence and explanation on accuracy and trust calibration in AI-assisted decision making (2020) · cites this paper as [17]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“observing the results reported by correct versus incorrect model decisions, all these features increased participants willingness to accept the AI's prediction regardless of its correctness, which is evidence that they are ineffective in calibrating trust.”
From Effect of confidence and explanation on accuracy and trust calibration in AI-assisted decision making (2020) · cites this paper as [17]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“This is in contrast to [17] where the humans performed substantially worse than the AI (by 37%).”
From Effect of confidence and explanation on accuracy and trust calibration in AI-assisted decision making (2020) · cites this paper as [17]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“while research repeatedly demonstrates that providing high-performance indicators of an AI system, such as showing high accuracy scores, could enhance people's trust and acceptance of the system [17, 30, 32]”
From Effect of confidence and explanation on accuracy and trust calibration in AI-assisted decision making (2020) · cites this paper as [17]
Experimental — accuracy not yet measured
45 more claims about this paper
Create a free account to see every claim other papers make about this one.
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 Unified Approach to Interpreting Model Predictions
Lundberg, S., & Lee, S.-I. (2017) · arXiv · doi:10.48550/arxiv.1705.07874 · Cited by 23,707 · cited 3×
“We build on recent developments in interpretable machine learning that provide useful frameworks for generating explanations of machine predictions [34, 35, 45, 50, 64, 65].”
BackgroundMethodDelving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.123 · Cited by 19,741 · cited 1×
“9%) [29]; Kleinberg et al.”
"Why Should I Trust You?": Explaining the Predictions of Any Classifier
Ribeiro, M. T., Singh, S., & Guestrin, C. (2016) · Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2939672.2939778 · Cited by 17,555
Gauriat, C.-M., Pencolé, Y., Ribot, P., & Brouillet, G. (2024) · HAL (Le Centre pour la Communication Scientifique Directe) · doi:10.4230/oasics.dx.2024.27 · Cited by 12,586
The spread of true and false news online
Vosoughi, S., Roy, D., & Aral, S. (2018) · Science · doi:10.1126/science.aap9559 · Cited by 8,847 · cited 2×
“nternet. For instance, Ott et al. [58] find that deceptive reviews are a growing problem on multiple platforms such as TripAdvisor and Yelp. Fake news has also received significant attention recently [43, 74] and might have influenced the outcome of the U.S. presidential election in 2016 [3]. Enhancing humans’ ability…”
BackgroundStatistical Decision Theory and Bayesian Analysis
Berger, J. O. (1985) · Springer Series in Statistics · doi:10.1007/978-1-4757-4286-2 · Cited by 7,722 · cited 1×
“knowledge databases and representations to reason about complex decisions [5, 31, 33, 55, 67].”
BackgroundAn introduction to cybernetics
Ashby, W. R. (1956) · doi:10.5962/bhl.title.5851 · Cited by 7,578 · cited 1×
“Our work also resonates with the seminal work on mixed-initiative user interfaces [31] and intelligence augmentation [4].”
ResultAxten, N., Newell, A., & Simon, H. A. (1973) · Contemporary Sociology · doi:10.2307/2063712 · Cited by 6,834 · cited 1×
“knowledge databases and representations to reason about complex decisions [5, 31, 33, 55, 67].”
BackgroundSocial Media and Fake News in the 2016 Election
Allcott, H., & Gentzkow, M. (2017) · Journal of Economic Perspectives · doi:10.1257/jep.31.2.211 · Cited by 6,767 · cited 1×
“Fake news has also received significant attention recently [43, 74] and might have influenced the outcome of the U.S. presidential election in 2016 [3].”
Background“Why Should I Trust You?”: Explaining the Predictions of Any Classifier
Ribeiro, M., Singh, S., & Guestrin, C. (2016) · Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Demonstrations · doi:10.18653/v1/n16-3020 · Cited by 6,682
Research works printed but not linked: 5
- Diane Farsetta and Daniel Price . 2006. Fake TV news: Widespread and undisclosed . Center for Media and Democracy 6 ( 2006 ). Diane Farsetta and Daniel Price. 2006. Fake TV news: Widespread and undisclosed. Center for Media and Democracy 6 (2006).
- Robert M Krauss , Valerie Geller , and Christopher Olson . 1976 . Modalities and cues in the detection of deception . In Meeting of the American Psychological Association , Washington, DC. Robert M Krauss, Valerie Geller, and Christopher Olson. 1976. Modalities and cues in the detection of deception. In Meeting of the American Psychological Association, Washington, DC.
- Albert Mehrabian . 1971. Silent messages . Vol. 8 . Wadsworth Belmont , CA. Albert Mehrabian. 1971. Silent messages. Vol. 8. Wadsworth Belmont, CA.
- 10.1037/0096-3445.130.3.380 · doi:10.1037/0096-3445.130.3.380 · Paper page
- Christopher D Wickens , Justin G Hollands , Simon Banbury , and Raja Parasuraman . 2015. Engineering psychology & human performance . Psychology Press . Christopher D Wickens, Justin G Hollands, Simon Banbury, and Raja Parasuraman. 2015. Engineering psychology & human performance. Psychology Press.
Cited by
Buçinca, Z., Malaya, M. B., & Gajos, K. Z. (2021) · arXiv · doi:10.48550/arxiv.2102.09692 · Cited by 1,124
“Consistent with prior research [7, 9, 26, 41], our results demonstrate that people aided by simple explainable AI interfaces performed better overall than people who completed the task without any AI support.”
BackgroundResultInfluentialDoes 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
“ge-scale study provides informative insights that will inform future work on these domains. Finally, we only explored a small fraction of possible ways to present explanations: highlighting key words [18, 36, 42, 62] and natural language arguments. It may be that alternative approaches provide more benefit to team per…”
BackgroundInfluentialZhang, Y., Liao, Q. V., & Bellamy, R. K. E. (2020) · Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency · doi:10.1145/3351095.3372852 · Cited by 895
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
“ge-scale study provides informative insights that will inform future work on these domains. Finally, we only explored a small fraction of possible ways to present explanations: highlighting key words [18, 36, 42, 62] and natural language arguments. It may be that alternative approaches provide more benefit to team per…”
BackgroundInfluentialWill Humans-in-the-Loop Become Borgs? Merits and Pitfalls of Working with AI
Fügener, A., Grahl, J., Gupta, A., & Ketter, W. (2021) · MIS Quarterly · doi:10.25300/misq/2021/16553 · Cited by 469
“In a deception detection experiment, where genuine and deceptive hotel reviews have to be classified, Lai and Tan (2019) find that adding explanatory information to AI suggestions significantly increases performance.”
Background
Metadata
- Authors
- Lai, V., & Tan, C.
- Affiliations
- University of Colorado Boulder (US)
- ORCID
- Tan, Chenhao
- Venue
- Proceedings of the Conference on Fairness, Accountability, and Transparency
- Publisher
- ACM
- Published
- 2019-01-29
- Pages
- 29-38
- OpenAlex
- W2901895173
- Semantic Scholar
- 127c1cb96b73399f429de553d315561504cc7cd4
- Cited by
- 377
- References
- 85
- Citations by year
- 2026: 55 · 2025: 53 · 2024: 73 · 2023: 65 · 2022: 54 · 2021: 41 · 2020: 26 · 2019: 9
- FWCI
- 12.43
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- ACM Conference on Fairness, Accountability, and Transparency (FAccT) (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Physical Sciences › Computer Science › Artificial Intelligence › Ethics and Social Impacts of AI
- Social Sciences › Human Factors and Ergonomics › Human-Automation Interaction and Safety
- Keywords
- human-machine decision-making, explainable machine learning, human prediction, machine learning prediction, human agency, human performance, recidivism prediction, diagnosis, fake news detection
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: On Human Predictions with Explanations and Predictions of Machine Learning Models: A Case Study on Deception Detection. https://app.cochat.ai/papers/10.1145/3287560.3287590
- The paper
- Lai, V., & Tan, C. (2019). On Human Predictions with Explanations and Predictions of Machine Learning Models: A Case Study on Deception Detection. Proceedings of the Conference on Fairness, Accountability, and Transparency. https://doi.org/10.1145/3287560.3287590
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.