Effect of confidence and explanation on accuracy and trust calibration in AI-assisted decision making
Open accessThe DOI matches its Crossref record; 32 of the 32 references it cites were found in a registry or an index; 23 of the 42 sources its claims cite were checked for support.
Abstract
Today, AI is being increasingly used to help human experts make decisions in high-stakes scenarios. In these scenarios, full automation is often undesirable, not only due to the significance of the outcome, but also because human experts can draw on their domain knowledge complementary to the model's to ensure task success. We refer to these scenarios as AI-assisted decision making, where the individual strengths of the human and the AI come together to optimize the joint decision outcome. A key to their success is to appropriately calibrate human trust in the AI on a case-by-case basis; knowing when to trust or distrust the AI allows the human expert to appropriately apply their knowledge, improving decision outcomes in cases where the model is likely to perform poorly. This research conducts a case study of AI-assisted decision making in which humans and AI have comparable performance alone, and explores whether features that reveal case-specific model information can calibrate trust and improve the joint performance of the human and AI. Specifically, we study the effect of showing confidence score and local explanation for a particular prediction. Through two human experiments, we show that confidence score can help calibrate people's trust in an AI model, but trust calibration alone is not sufficient to improve AI-assisted decision making, which may also depend on whether the human can bring in enough unique knowledge to complement the AI's errors. We also highlight the problems in using local explanation for AI-assisted decision making scenarios and invite the research community to explore new approaches to explainability for calibrating human trust in AI.
Overview
CoChat Summary
## TL;DR
This paper studies whether showing case-specific AI confidence scores and local explanations helps people calibrate trust in AI-assisted income prediction. Confidence scores improved trust calibration, but neither confidence nor explanations improved the joint decision accuracy.
## Key findings
- In Experiment 1, showing AI confidence scores significantly improved trust calibration: the main effect of showing confidence on switch percentage was significant, F(1,64) = 4.64, p = .035, and the interaction with confidence level was significant, F(4,256) = 15.8, p < .001.
- Trust calibration held whether or not the AI prediction was shown: the three-way interaction between confidence, prediction, and confidence level was not significant, F(4,256) = 0.266, p = .899.
- Showing confidence did not improve AI-assisted accuracy: there was no significant difference across prediction and confidence conditions, and H2 was rejected.
- In Experiment 2, local explanations did not improve trust calibration or accuracy: switch percentage showed no significant difference between explanation and baseline (p = .66), and AI-assisted accuracy also did not differ significantly across conditions, F(2,24) = 0.810, p = .457.
## Methods
- Two human-subject experiments on an AI-assisted binary income prediction task using the UCI Adult dataset (48,842 instances, 14 attributes); participants predicted whether annual income exceeded $50K.
- Experiment 1 recruited 72 Amazon Mechanical Turk participants and used a 2×2×2 design: show vs. not show AI confidence, show vs. not show AI prediction, and full vs. partial model, with 8 conditions and 9 participants per condition.
- Experiment 2 recruited 9 participants and used local explanations generated by the Shapley method; analysis relied on behavioral trust measures (switch percentage, agreement percentage) and ANOVA.
## Limitations
- The paper states that participants were not experts in income prediction; this was mitigated with training and domain statistics, but experts would be more realistic and were not used.
- The task was contrived and participants were not actually responsible for real outcomes; the authors partially mitigated this with bonus incentives, but note that more realistic high-stakes studies would need caution.
- The method for calibrating trust via confidence depends on model probabilities being well calibrated; the paper notes this may not hold for some models such as SVM, though Platt scaling or isotonic regression could address it.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
21 Valid · 3 Not valid · 6 Not checked · 64 Own results and interpretations
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“First, the decision performance was linked to monetary bonus, with a reward of 5 cents if the final prediction was correct and a loss of 2 cents if otherwise (in addition to a base pay of $3). Prior research showed that such a reward design is effective in motivating participants to optimize the decision outcome [2, 31]”
What the sources say
- Supportedcites [2] [2] Gagan Bansal, Besmira Nushi, Ece Kamar, Dan Weld, Walter Lasecki, and Eric Horvitz. 2019. Updates in Human-AI Teams: Understanding and Addressing the Performance/Compatibility Tradeoff. In AAAI Conference on Artificial Intelligence . AAAI. https://www.microsoft.com/enus/research/publication/updates-in-human-ai-teams-understanding-andaddressing-the-performance-compatibility-tradeoff/ - source
The Experiments section (pp. 4–5) describes monetary rewards and penalties tied to workers’ decisions. It says the payoff design was a good incentive to learn when to trust the AI and that doing so was the only way to earn a higher score. The citing paper’s specific 5-cent reward and 2-cent loss are its own design, not amounts attributed to this source. (LLM, conf=0.88)
- Partly supportedcites [31] [31] Forrest W Young. 1967. Twelve-choice probability learning with payoffs. Psychonomic Science 7, 10 (1967), 353-354. - sourceExperimental — accuracy not yet measured
The introduction (p. 1) reports that monetary payoffs led participants in earlier experiments to more nearly maximize earnings, and the Results and Discussion (p. 2) show that choices in this study strongly reflected expected values. But this study did not test the cited reward design: its methods (p. 2) state that incorrect predictions incurred no loss, whereas the citing sentence describes a two-cent loss. (LLM, conf=0.84)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“A key to success in AI-assisted decision making is to form a correct mental model of the model's error boundaries [2].”
What the sources say
- Supportedcites [2] [2] Gagan Bansal, Besmira Nushi, Ece Kamar, Dan Weld, Walter Lasecki, and Eric Horvitz. 2019. Updates in Human-AI Teams: Understanding and Addressing the Performance/Compatibility Tradeoff. In AAAI Conference on Artificial Intelligence . AAAI. https://www.microsoft.com/enus/research/publication/updates-in-human-ai-teams-understanding-andaddressing-the-performance-compatibility-tradeoff/ - source
The Introduction (p. 1) says that successful AI-assisted decisions depend on knowing when to follow or override the AI, which generally requires a mental model of when to trust it. The Q1 section (p. 5) reports that workers whose mental models matched the AI’s true error boundary had the highest team performance. (LLM, conf=0.92)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
The sources with a verdict support this claim; the rest weren’t checked yet, have no full text we could read, or their verdicts aren’t rated yet.
In the paper
“In contrast, prior works studying AI-assisted decision-making often used setups where humans' decision performance was significantly inferior than the model's [17, 30], which would by default reward people to rely on the AI.”
What the sources say
- Supportedcites [17] [17] Vivian Lai and Chenhao Tan. 2019. On Human Predictions with Explanations and Predictions of Machine Learning Models. In Proceedings of the Conference on Fairness, Accountability, and Transparency - FAT* '19 . ACM Press, New York, New York, USA, 29-38. https://doi.org/10.1145/3287560.3287590 - source
This paper is an example of the setup described. The Experimental Setup (p. 3) reports a model accuracy of 87% and says machine performance surpassed human performance of about 50% by a wide margin; the Concluding Discussion (p. 9) makes the same comparison. (LLM, conf=0.92)
- Not checked — no full text of the sourcecites [30] [30] Ming Yin, Jennifer Wortman Vaughan, and Hanna Wallach. 2019. Understanding the effect of accuracy on trust in machine learning models. In Conference on Human Factors in Computing Systems - Proceedings . Association for Computing Machinery. https://doi.org/10.1145/3290605.3300509 - source
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“several recent empirical studies found little evidence that the level of transparency has significant impact on people's willingness to trust a ML system, whether by using a directly interpretable model, allowing user to inspect the model behavior, showing explanation or reducing the number of features presented [5, 16, 27, 29].”
What the sources say
- Not checked — no full text of the sourcecites [5] [5] Hao Fei Cheng, Ruotong Wang, Zheng Zhang, Fiona O'Connell, Terrance Gray, F. Maxwell Harper, and Haiyi Zhu. 2019. Explaining decision-making algorithms through UI: Strategies to help non-expert stakeholders. In Conference on Human Factors in Computing Systems - Proceedings . Association for Computing Machinery. https://doi.org/10.1145/3290605.3300789 - source
- Not checked — no full text of the sourcecites [16] [16] Johannes Kunkel, Tim Donkers, Lisa Michael, Catalin-Mihai Barbu, and Jürgen Ziegler. 2019. Let Me Explain: Impact of Personal and Impersonal Explanations on Trust in Recommender Systems. In Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems . ACM, 487. - source
- Partly supportedcites [27] [27] Forough Poursabzi-Sangdeh, Daniel G Goldstein, Jake M Hofman, Jennifer Wortman Vaughan, and Hanna Wallach. 2018. Manipulating and Measuring Model Interpretability. (feb 2018). arXiv:1802.07810 https://arxiv.org/pdf/1802.07810. pdfhttp://arxiv.org/abs/1802.07810 - sourceExperimental — accuracy not yet measured
The Discussion and Conclusion (page unavailable) reports no significant improvement in how closely participants followed a clear, few-feature model’s predictions compared with a black-box, more-feature model. That supports the claim about reliance on predictions, but not an unqualified claim about willingness to trust: section 3.2 reports significantly greater stated confidence in predictions from the clear, two-feature model. This paper tested model transparency and feature count, not all the approaches listed in the citing sentence. (LLM, conf=0.87)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Every source the paper cites for this claim was checked and supports it.
In the paper
“frequently updating the AI algorithm may cause confusion to the human decision-maker, who may accept or reject the AI's recommendations at a wrong time, even if the algorithm's overall performance improved [2].”
What the sources say
- Supportedcites [2] [2] Gagan Bansal, Besmira Nushi, Ece Kamar, Dan Weld, Walter Lasecki, and Eric Horvitz. 2019. Updates in Human-AI Teams: Understanding and Addressing the Performance/Compatibility Tradeoff. In AAAI Conference on Artificial Intelligence . AAAI. https://www.microsoft.com/enus/research/publication/updates-in-human-ai-teams-understanding-andaddressing-the-performance-compatibility-tradeoff/ - source
The Introduction (p. 1) says team success depends on the human knowing when to follow or override AI recommendations, and that updates can disrupt those expectations even when AI performance improves. The patient-readmission example (p. 2) shows a more accurate updated classifier leading a doctor with an outdated mental model to take wrong actions. The Discussion (p. 8) also notes that developers may push updates frequently. (LLM, conf=0.91)
hedgedstates a possible cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
46 more claims · 3 with their cited sources checked
Create a free account to see all 94 claims and every source verdict.
- Probably not a substantial claim. 28
- It may state two separate claims as one. 26
- The quote only partly states this claim. 2
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
“On the contrary, several studies found that showing feature-based explanations increases people's tendency to over-rely on the model when it is wrong, compared to showing only the AI predictions [4,68,82,87].”
From Understanding the Role of Human Intuition on Reliance in Human-AI Decision-Making with Explanations (2023) · cites this paper as [87]
Checked by a reasoning model — may be wrong.
Experimental — accuracy not yet measuredThe cited source doesn’t support the claim as written.
In the citing paper
“since the mere presence of an explanation increases AI trust (Zhang, Liao, and Bellamy 2020).”
From Human-Clinical AI Agent Collaboration (2025) · cites this paper as Zhang, Liao, and Bellamy 2020
Checked by a reasoning model — may be wrong.
Experimental — accuracy not yet measuredThe cited source doesn’t support the claim as written.
In the citing paper
“This is achieved by, for example, presenting information about a system's confdence throughout the interaction [90, 104, 145] using cues or warning signals or by increasing a system's transparency through explanations [108].”
From Measuring and Understanding Trust Calibrations for Automated Systems: A Survey of the State-Of-The-Art and Future Directions (2023) · cites this paper as [145]
Checked by a reasoning model — may be wrong.
Experimental — accuracy not yet measuredThe cited source doesn’t support the claim as written.
In the citing paper
“Potential cognitive mechanisms that underlie these results suggest that the mere presence of an explanation increases trust [96,97], and that explanations anchor humans to the prediction [9,91].”
From Explanations Can Reduce Overreliance on AI Systems During Decision-Making (2023) · cites this paper as [97]
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 communicating explanations, on average, is not improving trust calibration, i.e., users still end-up in situations where they over-trust or under-trust AI-based recommendation.”
From Explainable recommendation: when design meets trust calibration (2021) · cites this paper as [96]
Experimental — accuracy not yet measured
53 more claims about this paper
Create a free account to see every claim other papers make about this one.
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
"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
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
Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI)
Adadi, A., & Berrada, M. (2018) · IEEE Access · doi:10.1109/access.2018.2870052 · Cited by 6,294
Developing and validating trust measures for e-commerce: an integrative typology
McKnight, D. H., Choudhury, V., & Kacmar, C. (2002) · Information Systems Research · doi:10.1287/isre.13.3.334.81 · Cited by 5,550 · cited 1×
“The concept of trust has its roots in relationships between humans, reflected in many aspects of collaborative behaviors with others such as willingness to depend, give information and make purchase [12, 21].”
BackgroundExplanation in Artificial Intelligence: Insights from the Social Sciences
Miller, T. (2017) · arXiv · doi:10.48550/arxiv.1706.07269 · Cited by 5,338
Deep neural networks are easily fooled: High confidence predictions for unrecognizable images
Nguyen, A., Yosinski, J., & Clune, J. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298640 · Cited by 3,258
Algorithm 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
Towards A Rigorous Science of Interpretable Machine Learning
Doshi-Velez, F., & Kim, B. (2017) · arXiv · doi:10.48550/arxiv.1702.08608 · Cited by 3,121
Predicting good probabilities with supervised learning
Niculescu-Mizil, A., & Caruana, R. (2005) · Proceedings of the 22nd international conference on Machine learning - ICML '05 · doi:10.1145/1102351.1102430 · Cited by 1,884
Machine Learning Interpretability: A Survey on Methods and Metrics
Carvalho, D. V., Pereira, E. M., & Cardoso, J. S. (2019) · Electronics · doi:10.3390/electronics8080832 · Cited by 1,842
O'Donovan, J., & Smyth, B. (2005) · Proceedings of the 10th international conference on Intelligent user interfaces · doi:10.1145/1040830.1040870 · Cited by 865
Manipulating 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
A Survey of Methods for Explaining Black Box Models
Guidotti, R., Monreale, A., Ruggieri, S., Turini, F., Giannotti, F., & Pedreschi, D. (2019) · ACM Computing Surveys · doi:10.1145/3236009 · Cited by 629
Understanding the Effect of Accuracy on Trust in Machine Learning Models
Yin, M., Wortman Vaughan, J., & Wallach, H. (2019) · Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3290605.3300509 · Cited by 527 · cited 5×
“…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], they may not help people distinguish cases they can trust from those they should not.”
BackgroundMethodResultInfluentialMetrics for explainable AI: challenges and prospects
Hoffman, R. R., Mueller, S. T., Klein, G., & Litman, J. (2018) · arXiv · doi:10.48550/arxiv.1812.04608 · Cited by 518
Lai, V., & Tan, C. (2019) · Proceedings of the Conference on Fairness, Accountability, and Transparency · doi:10.1145/3287560.3287590 · Cited by 377
Algorithm Aversion: People Erroneously Avoid Algorithms after Seeing Them ErrPreprint
Dietvorst, B. J., Simmons, J. P., & Massey, C. (2014) · SSRN Electronic Journal · doi:10.2139/ssrn.2466040 · Cited by 356
Explaining Decision-Making Algorithms through UI: Strategies to Help Non-Expert Stakeholders
Cheng, H.-F., Wang, R., Zhang, Z., O'Connell, F., Gray, T., Harper, F. M., & Zhu, H. (2019) · Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3290605.3300789 · Cited by 292 · cited 1×
“ople’s willingness to trust a ML system, whether by using a directly interpretable model, allowing user to inspect the model behavior, showing explanation or reducing the number of features presented [5, 16, 27, 29]. Many reasons could have contributed to this lack of effect. One is the complex mechanism driving trust…”
BackgroundHelldin, T., Falkman, G., Riveiro, M., & Davidsson, S. (2013) · Proceedings of the 5th International Conference on Automotive User Interfaces and Interactive Vehicular Applications · doi:10.1145/2516540.2516554 · Cited by 286 · cited 1×
“While the concept of trust calibration has been studied for automation [13, 18, 20, 26], as to prevent both automation aversion and automation bias, it is not well understood in the context of AI systems.”
BackgroundExplaining models: an empirical study of how explanations impact fairness judgment
Dodge, J., Liao, Q. V., Zhang, Y., Bellamy, R. K. E., & Dugan, C. (2019) · Proceedings of the 24th International Conference on Intelligent User Interfaces · doi:10.1145/3301275.3302310 · Cited by 286
Self-citationUpdates in Human-AI Teams: Understanding and Addressing the Performance/Compatibility Tradeoff
Bansal, G., Nushi, B., Kamar, E., Weld, D. S., Lasecki, W. S., & Horvitz, E. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33012429 · Cited by 284 · cited 5×
“[2] to test mental modeling of error boundaries.”
BackgroundInfluentialAutomation Bias in Intelligent Time Critical Decision Support Systems
Cummings, M. (2004) · AIAA 1st Intelligent Systems Technical Conference · doi:10.2514/6.2004-6313 · Cited by 269 · cited 3×
“of "automation bias" with which people overly rely on delegation to algorithms [6].”
BackgroundThe effects of example-based explanations in a machine learning interface
Cai, C. J., Jongejan, J., & Holbrook, J. (2019) · Proceedings of the 24th International Conference on Intelligent User Interfaces · doi:10.1145/3301275.3302289 · Cited by 220 · cited 1×
“[3] found that comparative explanation, by comparisons with examples in alternative classes, can lead to better discovery of the limitations of the AI, compared to normative explanation that describes examples in the intended”
McGuirl, J. M., & Sarter, N. B. (2006) · Human Factors: The Journal of the Human Factors and Ergonomics Society · doi:10.1518/001872006779166334 · Cited by 212
Let Me Explain: Impact of Personal and Impersonal Explanations on Trust in Recommender Systems
Kunkel, J., Donkers, T., Michael, L., Barbu, C.-M., & Ziegler, J. (2019) · Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3290605.3300717 · Cited by 156
I can do better than your AI: expertise and explanations
Schaffer, J., O'Donovan, J., Michaelis, J., Raglin, A., & Höllerer, T. (2019) · Proceedings of the 24th International Conference on Intelligent User Interfaces · doi:10.1145/3301275.3302308 · Cited by 119
Individual Differences in the Calibration of Trust in Automation
Pop, V. L., Shrewsbury, A., & Durso, F. T. (2015) · Human Factors: The Journal of the Human Factors and Ergonomics Society · doi:10.1177/0018720814564422 · Cited by 109
Do I trust my machine teammate?: an investigation from perception to decision
Yu, K., Berkovsky, S., Taib, R., Zhou, J., & Chen, F. (2019) · Proceedings of the 24th International Conference on Intelligent User Interfaces · doi:10.1145/3301275.3302277 · Cited by 71
Type of Automation Failure: The Effects on Trust and Reliance in Automation
Johnson, J. D., Sanchez, J., Fisk, A. D., & Rogers, W. A. (2004) · Proceedings of the Human Factors and Ergonomics Society Annual Meeting · doi:10.1177/154193120404801807 · Cited by 41
Type of automation failure: The effects on trust and reliance in automation
Johnson, J. D., Sánchez, J., Fisk, A. D., & Rogers, W. A. (2004) · PsycEXTRA Dataset · doi:10.1037/e577212012-007 · Cited by 18
Twelve-choice probability learning with payoffs
Young, F. W. (1967) · Psychonomic Science · doi:10.3758/bf03331120 · Cited by 8
Cited by
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. S. (2020) · arXiv · doi:10.48550/arxiv.2006.14779 · Cited by 754
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
“Income category [83] Accuracy ↑ 65% 75% 73% ✗”
BackgroundMethodVaithilingam, P., Zhang, T., & Glassman, E. L. (2022) · CHI Conference on Human Factors in Computing Systems Extended Abstracts · doi:10.1145/3491101.3519665 · Cited by 660
When combinations of humans and AI are useful: A systematic review and meta-analysis
Vaccaro, M., Almaatouq, A., & Malone, T. (2024) · Nature Human Behaviour · doi:10.1038/s41562-024-02024-1 · Cited by 570
“But some studies show that augmenting humans with AI can lead to better outcomes than humans or AI working alone 24–26 , while others show the opposite 4,7,9 .”
Large Legal Fictions: Profiling Legal Hallucinations in Large Language Models
Dahl, M., Magesh, V., Suzgun, M., & Ho, D. E. (2024) · Journal of Legal Analysis · doi:10.1093/jla/laae003 · Cited by 559
Metadata
- Authors
- Zhang, Y., Liao, Q. V., & Bellamy, R. K. E.
- Affiliations
- IBM (United States) (US)
- Venue
- Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency
- Publisher
- ACM
- Published
- 2020-01-27
- Pages
- 295-305
- OpenAlex
- W2999637955
- Semantic Scholar
- 5cc4100a67fd6f2ce3c760655ba7a12f358c7950
- Cited by
- 895
- References
- 25
- Citations by year
- 2026: 229 · 2025: 163 · 2024: 198 · 2023: 128 · 2022: 89 · 2021: 71 · 2020: 17
- FWCI
- 29.12
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- ACM Conference on Fairness, Accountability, and Transparency (FAccT) (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Social Sciences › Human Factors and Ergonomics › Human-Automation Interaction and Safety
- Physical Sciences › Computer Science › Artificial Intelligence › Ethics and Social Impacts of AI
- Keywords
- AI-assisted decision-making, trust calibration, confidence scores, local explanations, explainability, human-AI collaboration, human expertise, trust in AI
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.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-09-29, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-09-29 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
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.