How do visual explanations foster end users' appropriate trust in machine learning?
Published version of a preprint
The DOI matches its Crossref record; 97 of the 97 references it cites were found in a registry or an index.
Abstract
We investigated the effects of example-based explanations for a machine learning classifier on end users' appropriate trust. We explored the effects of spatial layout and visual representation in an in-person user study with 33 participants. We measured participants' appropriate trust in the classifier, quantified the effects of different spatial layouts and visual representations, and observed changes in users' trust over time. The results show that each explanation improved users' trust in the classifier, and the combination of explanation, human, and classification algorithm yielded much better decisions than the human and classification algorithm separately. Yet these visual explanations lead to different levels of trust and may cause inappropriate trust if an explanation is difficult to understand. Visual representation and performance feedback strongly affect users' trust, and spatial layout shows a moderate effect. Our results do not support that individual differences (e.g., propensity to trust) affect users' trust in the classifier. This work advances the state-of-the-art in trust-able machine learning and informs the design and appropriate use of automated systems.
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, many empirical studies on human-AI decision-making did not observe complementary performance [6,16,37,52,58,61,68,82,84,87].”
From Understanding the Role of Human Intuition on Reliance in Human-AI Decision-Making with Explanations (2023) · cites this paper as [84]
In the citing paper
“Existing literature is ambiguous with regard to effects of explanations [3, 6, 74]: While in some experiments, explanations support AR [74, 75], in others they cause 'blind trust' [3, 6] in AI advice.”
From Appropriate Reliance on AI Advice: Conceptualization and the Effect of Explanations (2023) · cites this paper as [75]
In the citing paper
“In addition, some studies also employed linear trust meters [137], or visual analog scales [139].”
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 [137]
In the citing paper
“A third way to measure the trust calibration was to measure over-, under-, and appropriate trust as the behavioral deviation (reliance) from the ideal behavior [27,50,55,104,110,132,137].”
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 [137]
In the citing paper
“In contrast, Yang et al. [137] found that visual explanations supported an appropriate trust calibration.”
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 [137]
1 more claim about this paper
Create a free account to see every claim other papers make about this one.
Citations
Cites
"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
An integrative model of organizational trust
Mayer, R. C., Davis, J. H., & Schoorman, F. D. (1995) · The Academy of Management Review · doi:10.2307/258792 · Cited by 10,736 · cited 1×
“While many definitions and models of trust were proposed[81, 119] in different contexts (e.g., human-human[70, 77], human-automation[37, 62, 93], and e-commerce[32, 64]), we use the definition for human-computer trust from Madsen and Gregor[72] which was adapted from McAllister[78]: “…”
MethodGeurts, P., Ernst, D., & Wehenkel, L. (2006) · Machine Learning · doi:10.1007/s10994-006-6226-1 · Cited by 9,300 · cited 1×
“…coefficients for a linear support-vector classifier[28], showing the distribution of selected features across the random trees for the importance of features in an extra-trees classifier[33], and explaining the inner working of an artificial neural network for overall variable contributions[95].”
BackgroundScikit-learn: Machine Learning in Python
(2011) · Journal of Machine Learning Research · doi:10.5555/1953048.2078195 · Cited by 8,539
Affect and Cognition Based Trust as Foundations for Interpersonal Cooperation in Organizations
McAllister, D. J. (1995) · Academy of Management Journal · doi:10.2307/256727 · Cited by 7,346
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 5×
“While many definitions and models of trust were proposed[81, 119] in different contexts (e.g., human-human[70, 77], human-automation[37, 62, 93], and e-commerce[32, 64]), we use the definition for human-computer trust from Madsen and Gregor[72] which was adapted from McAllister[78]: “…”
BackgroundMethodInfluentialDeep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
Simonyan, K., Vedaldi, A., & Zisserman, A. (2013) · arXiv · doi:10.48550/arxiv.1312.6034 · Cited by 5,370 · cited 1×
“Other techniques delved into the black-box to explain the classifier[106], assisted machine learning experts to understand the classifier’s internal representation[26, 73, 124], and deep neural networks’ architecture[50, 121].”
MethodExplanation in artificial intelligence: Insights from the social sciences
Miller, T. (2019) · Artificial Intelligence · doi:10.1016/j.artint.2018.07.007 · Cited by 5,302
E-commerce: the role of familiarity and trust.
Gefen, D. (2000) · Omega · doi:10.1016/s0305-0483(00)00021-9 · Cited by 3,529 · cited 1×
“We referred to two ways in the literature to measure trust: (1) directly reporting the level of trust using subjective rating scales (e.g.,[14, 29, 31, 60, 126]); and (2) measuring through a multi-item questionnaire (e.g.,[47, 78, 82, 85, 87, 100, 104]).”
MethodAlgorithm 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 · cited 2×
“Empirically, example-based explanations helped users with diverse backgrounds better understand and access an intelligent system[8, 11, 18].”
BackgroundThe New Statistics: Why and How
Cumming, G. (2014) · Psychological Science · doi:10.1177/0956797613504966 · Cited by 3,200
Rempel, J. K., Holmes, J. G., & Zanna, M. P. (1985) · Journal of Personality and Social Psychology · doi:10.1037/0022-3514.49.1.95 · Cited by 3,146 · cited 1×
“We referred to two ways in the literature to measure trust: (1) directly reporting the level of trust using subjective rating scales (e.g.,[14, 29, 31, 60, 126]); and (2) measuring through a multi-item questionnaire (e.g.,[47, 78, 82, 85, 87, 100, 104]).”
Method(2011) · Cited by 2,025
A trust model for consumer Internet shopping
Lee, M. K. O., & Turban, E. (2001) · International Journal of Electronic Commerce · doi:10.1080/10864415.2001.11044227 · Cited by 2,012 · cited 1×
“…and models of trust were proposed[81, 119] in different contexts (e.g., human-human[70, 77], human-automation[37, 62, 93], and e-commerce[32, 64]), we use the definition for human-computer trust from Madsen and Gregor[72] which was adapted from McAllister[78]: “ Human-computer trust is…”
MethodUnderstanding deep image representations by inverting them
Mahendran, A., & Vedaldi, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7299155 · Cited by 1,827
Foundations for an Empirically Determined Scale of Trust in Automated Systems
Jian, J.-Y., Bisantz, A. M., & Drury, C. G. (2000) · International Journal of Cognitive Ergonomics · doi:10.1207/s15327566ijce0401_04 · Cited by 1,799
Graph visualization and navigation in information visualization: A survey
Herman, I., Melancon, G., & Marshall, M. S. (2000) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/2945.841119 · Cited by 1,538 · cited 1×
“Layout (also known as position ) is a key factor in designing visualization[9] that affects people’s perception and cognition[40].”
BackgroundUnderstanding Black-box Predictions via Influence Functions
Koh, P. W., & Liang, P. (2017) · arXiv · doi:10.48550/arxiv.1703.04730 · Cited by 1,514 · cited 4×
“For example, a few techniques learned an influence function and used the most influential training instances[53, 122]; visual inspection was used to reveal important features and explain a prediction for both binary[112] and real-valued data[58]; a locally learned model was used to show an…”
BackgroundMethodInfluentialCognitive and affective trust in service relationships
Johnson, D., & Grayson, K. (2005) · Journal of Business Research · doi:10.1016/s0148-2963(03)00140-1 · Cited by 1,466 · cited 1×
“The first item captures more of cognitive trust , the willingness to rely on a system’s competence, which arises from accumulated knowledge[48].”
BackgroundTrust, control strategies and allocation of function in human-machine systems
LEE, J., & MORAY, N. (1992) · Ergonomics · doi:10.1080/00140139208967392 · Cited by 1,459 · cited 3×
“The accuracy of the classifier was 71%, which is of medium reliability/utility[17, 46, 60, 84, 89, 126] to foster trust in machine learning.”
BackgroundMethodLee, M. K. (2018) · Big Data & Society · doi:10.1177/2053951718756684 · Cited by 1,338 · cited 1×
“Users’ understanding of a system can correlate with their trust [63, 68], but their understanding does not necessarily equate to trust[7] or accurately predict their trust[52].”
BackgroundThe role of trust in automation reliance
Dzindolet, M. T., Peterson, S. A., Pomranky, R. A., Pierce, L. G., & Beck, H. P. (2003) · International Journal of Human-Computer Studies · doi:10.1016/s1071-5819(03)00038-7 · Cited by 1,276 · cited 2×
“These studies used verbal explanations (e.g., [21, 52, 117]) or showed a few examples/features (e.g.,[11, 66]) for end users[67] (e.g.,participants from Amazon’s Mechanical Turk[66]).”
BackgroundOlden, J. D., & Jackson, D. A. (2002) · Ecological Modelling · doi:10.1016/s0304-3800(02)00064-9 · Cited by 1,223 · cited 1×
“…coefficients for a linear support-vector classifier[28], showing the distribution of selected features across the random trees for the importance of features in an extra-trees classifier[33], and explaining the inner working of an artificial neural network for overall variable contributions[95].”
BackgroundA survey of trust in internet applications
Grandison, T., & Sloman, M. (2000) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2000.5340804 · Cited by 1,157 · cited 1×
“While many definitions and models of trust were proposed[81, 119] in different contexts (e.g., human-human[70, 77], human-automation[37, 62, 93], and e-commerce[32, 64]), we use the definition for human-computer trust from Madsen and Gregor[72] which was adapted from McAllister[78]: “…”
MethodMUIR, B. M., & MORAY, N. (1996) · Ergonomics · doi:10.1080/00140139608964474 · Cited by 993 · cited 1×
“Operators did not use automation when their trust in the system was less than their own self-confidence [61]; they used automated systems they trusted and did not use those they did not trust [94].”
MethodVisual interpretability for deep learning: a survey
Zhang, Q.-S., & Zhu, S.-C. (2018) · Frontiers of Information Technology & Electronic Engineering · doi:10.1631/fitee.1700808 · Cited by 950 · cited 1×
“visualization, artificial intelligence/machine learning) are arguing for more human interpretability of machine learning[19, 35, 42, 128] and beyond[3] and explored various ways of explaining machine”
BackgroundTrust, self-confidence, and operators' adaptation to automation
Lee, J. D., & Moray, N. (1994) · International Journal of Human-Computer Studies · doi:10.1006/ijhc.1994.1007 · Cited by 932 · cited 1×
“Operators did not use automation when their trust in the system was less than their own self-confidence [61]; they used automated systems they trusted and did not use those they did not trust [94].”
MethodDesigning Theory-Driven User-Centric Explainable AI
Wang, D., Yang, Q., Abdul, A., & Lim, B. Y. (2019) · Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3290605.3300831 · Cited by 906 · cited 2×
“Such explanations also align with people’s inductive (“bottom-up logic”) and analogical reasoning (“one instance to another”) to understand why certain objects are considered similar or different[116].”
BackgroundMUIR, B. M. (1994) · Ergonomics · doi:10.1080/00140139408964957 · Cited by 873 · cited 1×
“While many definitions and models of trust were proposed[81, 119] in different contexts (e.g., human-human[70, 77], human-automation[37, 62, 93], and e-commerce[32, 64]), we use the definition for human-computer trust from Madsen and Gregor[72] which was adapted from McAllister[78]: “…”
MethodTrust between humans and machines, and the design of decision aids
Muir, B. M. (1987) · International Journal of Man-Machine Studies · doi:10.1016/s0020-7373(87)80013-5 · Cited by 762 · cited 1×
“As such, appropriate trust (or calibrated trust[87, 92], see Figure 2) is the alignment between the perceived and actual performance of the system[79, 80].”
BackgroundAbdul, A., Vermeulen, J., Wang, D., Lim, B. Y., & Kankanhalli, M. (2018) · Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3173574.3174156 · Cited by 743
What Makes a Visualization Memorable?
Borkin, M. A., Vo, A. A., Bylinskii, Z., Isola, P., Sunkavalli, S., Oliva, A., & Pfister, H. (2013) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2013.234 · Cited by 666 · cited 1×
“…for three reasons: (1) grayscale images are more similar to rose charts (Figures 1a c.f. b) to avoid issues like differences in memorability[5], (2) colors are misleading because all the texture features (e.g., elongation) in the dataset were based on intensity, and (3) the color images…”
BackgroundHow Much Information?: Effects of Transparency on Trust in an Algorithmic Interface
Kizilcec, R. F. (2016) · Proceedings of the 2016 CHI Conference on Human Factors in Computing Systems · doi:10.1145/2858036.2858402 · Cited by 615
Visual Analytics in Deep Learning: An Interrogative Survey for the Next Frontiers
Hohman, F., Kahng, M., Pienta, R., & Chau, D. H. (2019) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2018.2843369 · Cited by 582
Similarities and differences between human–human and human–automation trust: an integrative review
Madhavan, P., & Wiegmann, D. A. (2007) · Theoretical Issues in Ergonomics Science · doi:10.1080/14639220500337708 · Cited by 577 · cited 2×
“Trust in a system is both similar to and different from trust in relationships between humans[62, 70].”
BackgroundMethodPrinciples of Explanatory Debugging to Personalize Interactive Machine Learning
Kulesza, T., Burnett, M., Wong, W.-K., & Stumpf, S. (2015) · Proceedings of the 20th International Conference on Intelligent User Interfaces · doi:10.1145/2678025.2701399 · Cited by 576 · cited 4×
“Kulesza et al. outlined a set of principles for designing explanations for interactive machine learning, i.e.,“Be Complete” and “Don’t Overwhelm”[59].”
BackgroundInfluentialGonzález-Gallardo, C. E., Montes, A., Sierra, G., Núñez-Juárez, J. A., Salinas-López, A. J., & Ek, J. (2015) · conference · Cited by 559
Why and why not explanations improve the intelligibility of context-aware intelligent systems
Lim, B. Y., Dey, A. K., & Avrahami, D. (2009) · Proceedings of the SIGCHI Conference on Human Factors in Computing Systems · doi:10.1145/1518701.1519023 · Cited by 552
Merritt, S. M., & Ilgen, D. R. (2008) · Human Factors: The Journal of the Human Factors and Ergonomics Society · doi:10.1518/001872008x288574 · Cited by 527 · cited 1×
“We did not manipulate other factors such as affect[84, 89] and workload[16], but we controlled reliability[65, 86, 117, 126], expectation[62], and risk[83].”
BackgroundResampling-Based Multiple Testing: Examples and Methods for p-Value Adjustment.
Thomas, G. E., Westfall, P. H., & Young, S. S. (1994) · The Statistician · doi:10.2307/2348369 · Cited by 513
Recommendation Agents for Electronic Commerce: Effects of Explanation Facilities on Trusting Beliefs
Wang, W., & Benbasat, I. (2007) · Journal of Management Information Systems · doi:10.2753/mis0742-1222230410 · Cited by 498 · cited 1×
“A current and widely held belief is that explaining to users how a system operates will improve their trust in the system[25, 34, 99, 118] and decrease aversion after seeing an error[18].”
BackgroundContextual variability and serial position effects in free recall.
Howard, M. W., & Kahana, M. J. (1999) · Journal of Experimental Psychology: Learning, Memory, and Cognition · doi:10.1037//0278-7393.25.4.923 · Cited by 469 · cited 1×
“…order to (1) compare with other experiments studied trust (e.g., 10[17, 22, 60, 84, 85]), 24/48[76], 26[17], 50[104]), (2) have enough trials to develop trust but prevent participants from memorizing the order (serial position effects[44]), (3) balance the number of trials across different classes.”
BackgroundThe Role of Explanations on Trust and Reliance in Clinical Decision Support Systems
Bussone, A., Stumpf, S., & O'Sullivan, D. (2015) · 2015 International Conference on Healthcare Informatics · doi:10.1109/ichi.2015.26 · Cited by 441 · cited 2×
“Users’ understanding of a system can correlate with their trust[63, 68], but their understanding does not necessarily equate to trust[7] or accurately predict their trust[52].”
BackgroundFalleti, M. G., Maruff, P., Collie, A., & Darby, D. G. (2006) · Journal of Clinical and Experimental Neuropsychology · doi:10.1080/13803390500205718 · Cited by 422 · cited 1×
“Each participant completed the two sub-experiments be-tween 2 and 5 days apart due to our strong concerns about learning, practice[ 27], and fatigue effects[102].”
MethodInteracting with Predictions: Visual Inspection of Black-box Machine Learning Models
Krause, J., Perer, A., & Ng, K. (2016) · Proceedings of the 2016 CHI Conference on Human Factors in Computing Systems · doi:10.1145/2858036.2858529 · Cited by 390
The Perceived Utility of Human and Automated Aids in a Visual Detection Task
Dzindolet, M. T., Pierce, L. G., Beck, H. P., & Dawe, L. A. (2002) · Human Factors: The Journal of the Human Factors and Ergonomics Society · doi:10.1518/0018720024494856 · Cited by 386
K-means with Three different Distance Metrics
Singh, A., Yadav, A., & Rana, A. (2013) · International Journal of Computer Applications · doi:10.5120/11430-6785 · Cited by 380 · cited 1×
“Our algorithm first constructs a k − nearest neighbors graph from the internal representation matrix of the training set combined with the input instance based on the Minkowski distance metric[107].”
MethodThe structure of the information visualization design space
Card, S. K., & Mackinlay, J. (2002) · Proceedings of VIZ '97: Visualization Conference, Information Visualization Symposium and Parallel Rendering Symposium · doi:10.1109/infvis.1997.636792 · Cited by 347 · cited 4×
“While these studies explored different design factors for explanations per se, few investigated visual properties of explanations, which are crucial in understanding and interpreting information from a visualization[9].”
BackgroundInfluentialActiVis: Visual Exploration of Industry-Scale Deep Neural Network Models
Kahng, M., Andrews, P. Y., Kalro, A., & Chau, D. H. (2018) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2017.2744718 · Cited by 337
Visualizing Dataflow Graphs of Deep Learning Models in TensorFlow
Wongsuphasawat, K., Smilkov, D., Wexler, J., Wilson, J., Mane, D., Fritz, D., Krishnan, D., Viegas, F. B., & Wattenberg, M. (2018) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2017.2744878 · Cited by 331
LIBLINEAR: A Library for Large Linear Classification
FanRong-En, ChangKai-Wei, HsiehCho-Jui, WangXiang-Rui, & LinChih-Jen (2008) · Journal of Machine Learning Research · doi:10.5555/1390681.1442794 · Cited by 328
Fair Statistical Communication in HCI
Dragicevic, P. (2016) · Human–Computer Interaction Series · doi:10.1007/978-3-319-26633-6_13 · Cited by 325
Trust and Deception in Virtual Societies
(2001) · Springer eBooks · doi:10.1007/978-94-017-3614-5 · Cited by 321
LineUp: Visual Analysis of Multi-Attribute Rankings
Gratzl, S., Lex, A., Gehlenborg, N., Pfister, H., & Streit, M. (2013) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2013.173 · Cited by 307 · cited 1×
“We were aware that bar[6, 38, 57, 108] and radar[127] charts were commonly used to show features, but little evidence supports that they are more effective than rose charts[56].”
MethodTrust building with explanation interfaces
Pu, P., & Chen, L. (2006) · Proceedings of the 11th international conference on Intelligent user interfaces · doi:10.1145/1111449.1111475 · Cited by 300 · cited 1×
“A current and widely held belief is that explaining to users how a system operates will improve their trust in the system[25, 34, 99, 118] and decrease aversion after seeing an error[18].”
BackgroundUpdates 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 1×
“Besides machine learning experts, many other end users can also benefit from machine learning[41, 129], and sometimes human-machine collaborations exhibit better performance than the human or the machine alone[4, 30, 115].”
Backgroundde Vries, P., Midden, C., & Bouwhuis, D. (2003) · International Journal of Human-Computer Studies · doi:10.1016/s1071-5819(03)00039-9 · Cited by 264 · cited 2×
“The accuracy of the classifier was 71%, which is of medium reliability/utility[17, 46, 60, 84, 89, 126] to foster trust in machine learning.”
BackgroundAffective Processes in Human–Automation Interactions
Merritt, S. M. (2011) · Human Factors: The Journal of the Human Factors and Ergonomics Society · doi:10.1177/0018720811411912 · Cited by 260 · cited 3×
“We did not manipulate other factors such as affect[84, 89] and workload[16], but we controlled reliability[65, 86, 117, 126], expectation[62], and risk[83].”
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 6×
“To do so, we investigated the relationship between users’ trust and visual explanations, namely example-based explanations (e.g., [8, 53, 55, 122]), which we argue are more suitable as explanations for end users.”
BackgroundMethodInfluentialThe Persuasive Power of Data Visualization
Pandey, A. V., Manivannan, A., Nov, O., Satterthwaite, M., & Bertini, E. (2014) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2014.2346419 · Cited by 217 · cited 1×
“Image-based explanations also mitigate under-trust; that is, they have persuasive power[96] to convince people to believe that a recommendation is correct.”
BackgroundExplainable Artificial Intelligence (XAI)
Mohaghegh, S. D. (2024) · Artificial Intelligence for Science and Engineering Applications · doi:10.1201/9781003369356-8 · Cited by 215
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 · cited 1×
“As such, appropriate trust (or calibrated trust[87, 92], see Figure 2) is the alignment between the perceived and actual performance of the system[79, 80].”
BackgroundToward establishing trust in adaptive agents
Glass, A., McGuinness, D. L., & Wolverton, M. (2008) · Proceedings of the 13th international conference on Intelligent user interfaces · doi:10.1145/1378773.1378804 · Cited by 211 · cited 1×
“A current and widely held belief is that explaining to users how a system operates will improve their trust in the system[25, 34, 99, 118] and decrease aversion after seeing an error[18].”
Backgroundde Visser, E., & Parasuraman, R. (2011) · Journal of Cognitive Engineering and Decision Making · doi:10.1177/1555343411410160 · Cited by 207
Dis-function: Learning distance functions interactively
Brown, E. T., Liu, J., Brodley, C. E., & Chang, R. (2012) · 2012 IEEE Conference on Visual Analytics Science and Technology (VAST) · doi:10.1109/vast.2012.6400486 · Cited by 193 · cited 1×
“We were aware that bar[6, 38, 57, 108] and radar[127] charts were commonly used to show features, but little evidence supports that they are more effective than rose charts[56].”
MethodTrust, Untrust, Distrust and Mistrust – An Exploration of the Dark(er) Side
Marsh, S., & Dibben, M. R. (2005) · Lecture Notes in Computer Science · doi:10.1007/11429760_2 · Cited by 188 · cited 1×
“Both disuse and misuse could cause serious problems[74, 79].”
BackgroundInteracting meaningfully with machine learning systems: Three experiments
Stumpf, S., Rajaram, V., Li, L., Wong, W.-K., Burnett, M., Dietterich, T., Sullivan, E., & Herlocker, J. (2009) · International Journal of Human-Computer Studies · doi:10.1016/j.ijhcs.2009.03.004 · Cited by 184 · cited 2×
“Other research showed that explanations sometimes hurt users’ performance[57], and multiple explanations may need to be considered[110].”
BackgroundInteractive decision making using dissimilarity to visually represented prototypes
Migut, M., van Gemert, J. V., & Worring, M. (2011) · IEEE Conference on Visual Analytics Science and Technology · doi:10.1109/vast.2011.6102451 · Cited by 171 · cited 1×
“Also, to improve the understandability of representations, interaction techniques[88] like brushing and coordinated multiple views[56] can be used to help users gain insights about features and further confidence scores from the classifier.”
INFUSE: Interactive Feature Selection for Predictive Modeling of High Dimensional Data
Krause, J., Perer, A., & Bertini, E. (2014) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2014.2346482 · Cited by 169 · cited 2×
“We were aware that bar[6, 38, 57, 108] and radar[127] charts were commonly used to show features, but little evidence supports that they are more effective than rose charts[56].”
MethodExplaining instance classifications with interactions of subsets of feature values
Štrumbelj, E., Kononenko, I., & Robnik‐Šikonja, M. (2009) · Data & Knowledge Engineering · doi:10.1016/j.datak.2009.01.004 · Cited by 152 · cited 1×
“We were aware that bar[6, 38, 57, 108] and radar[127] charts were commonly used to show features, but little evidence supports that they are more effective than rose charts[56].”
MethodA typology of career decision status: Validity extension of the vocational decision status model.
Wanberg, C. R., & Muchinsky, P. M. (1992) · Journal of Counseling Psychology · doi:10.1037/0022-0167.39.1.71 · Cited by 131 · cited 1×
“…replaced confident for two reasons: (1) the participants in pilot study were confused with whether confidence referred to the classifier or their decision; and (2) confident and comfortable are equivalent in conceptual meaning[114], while comfortable was used more to describe a decision[49, 114].”
BackgroundThe impact of cognitive feedback on judgment performance and trust with decision aids
Seong, Y., & Bisantz, A. M. (2008) · International Journal of Industrial Ergonomics · doi:10.1016/j.ergon.2008.01.007 · Cited by 129 · cited 3×
“Giving feedback calibrates trust such that we were able to measure appropriate trust[87], and it also compensates for a poor performing aid[104] because end users may not have expertise to accomplish the task in an early stage; last, showing feedback allows us to observe change of trust over time,…”
BackgroundMethodA Design Methodology for Trust Cue Calibration in Cognitive Agents
de Visser, E. J., Cohen, M. S., Freedy, A., & Parasuraman, R. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-07458-0_24 · Cited by 121
Evaluation of Features for Leaf Discrimination
Silva, P. F. B., Marcal, A. R. S., & Almeida, R. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-39094-4_23 · Cited by 117 · cited 2×
“We based our experiment on the UCI leaf dataset[105]; this dataset includes both expert engineered feature vectors and images so that we were able to vary instance representations in a controlled manner.”
MethodInfluentialVisual Diagnosis of Tree Boosting Methods
Liu, S., Xiao, J., Liu, J., Wang, X., Wu, J., & Zhu, J. (2017) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2017.2744378 · Cited by 109 · cited 1×
“However, much of the existing research focused on explaining the underlying algorithm[69]; and designers may assume that users have advanced knowledge of machine learning[69], or users have to understand the decision process (e.g.,[59, 67]).”
BackgroundMultiple subtypes among vocationally undecided college students: A model and assessment instrument.
Jones, L. K., & Chenery, M. F. (1980) · Journal of Counseling Psychology · doi:10.1037/0022-0167.27.5.469 · Cited by 106 · cited 1×
“Comfortable replaced confident for two reasons: (1) the participants in pilot study were confused with whether confidence referred to the classifier or their decision; and (2) confident and comfortable are equivalent in conceptual meaning[114], while comfortable was used more to describe a decision[49, 114].”
BackgroundAna, J. S., Franchini, É., da Silva, V., & Diefenthaeler, F. (2016) · Sports Biomechanics · doi:10.1080/14763141.2016.1217347 · Cited by 105 · cited 1×
“Each participant completed the two sub-experiments be-tween 2 and 5 days apart due to our strong concerns about learning, practice[ 27], and fatigue effects[102].”
Method(2018) · Human-computer interaction series · doi:10.1007/978-3-319-90403-0 · Cited by 104
Exploring the limits of complexity: A survey of empirical studies on graph visualisation
Yoghourdjian, V., Archambault, D., Diehl, S., Dwyer, T., Klein, K., Purchase, H. C., & Wu, H. (2018) · Visual Informatics · doi:10.1016/j.visinf.2018.12.006 · Cited by 93
Madni, A. M., & Madni, C. C. (2018) · Systems · doi:10.3390/systems6040044 · Cited by 89 · cited 1×
“1 Every explanation improves users’ appropriate trust in the classifier, and the human-machine collboration[71] can achieve nearly perfect performance (all good decisions) when an effective explanation is available.”
BackgroundInterpreting Black-Box Classifiers Using Instance-Level Visual Explanations
Tamagnini, P., Krause, J., Dasgupta, A., & Bertini, E. (2017) · Workshop on Human-In-the-Loop Data Analytics (HILDA) · doi:10.1145/3077257.3077260 · Cited by 86 · cited 1×
“For example, a few techniques learned an influence function and used the most influential training instances[53, 122]; visual inspection was used to reveal important features and explain a prediction for both binary[112] and real-valued data[58]; a locally learned model was used to show an instance-level prediction of…”
MethodExplaining Explanation, Part 1: Theoretical Foundations
Hoffman, R. R., & Klein, G. A. (2017) · IEEE Intelligent Systems · doi:10.1109/mis.2017.54 · Cited by 86 · cited 1×
“Several research communities (e.g., human-computer interaction, visualization, artificial intelligence/machine learning) are arguing for more human interpretability of machine learning[19, 35, 42, 128] and beyond[3] and explored various ways of explaining machine learning classification.”
BackgroundMerritt, S. M., Lee, D., Unnerstall, J. L., & Huber, K. (2015) · Human Factors: The Journal of the Human Factors and Ergonomics Society · doi:10.1177/0018720814561675 · Cited by 83 · cited 3×
“Giving feedback calibrates trust such that we were able to measure appropriate trust[87], and it also compensates for a poor performing aid[104] because end users may not have expertise to accomplish the task in an early stage; last, showing feedback allows us to observe change of trust over time,…”
BackgroundMethodExplainers: Expert Explorations with Crafted Projections
Gleicher, M. L. (2013) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2013.157 · Cited by 80 · cited 1×
“visualization, artificial intelligence/machine learning) are arguing for more human interpretability of machine learning[19, 35, 42, 128] and beyond[3] and explored various ways of explaining machine”
BackgroundBrains or Beauty: How to Engender Trust in User-Agent Interactions
Yuksel, B. F., Collisson, P., & Czerwinski, M. (2017) · ACM Transactions on Internet Technology · doi:10.1145/2998572 · Cited by 63
Transparent Data Mining for Big and Small Data
Cerquitelli, T., Cerquitelli, T., Quercia, D., & Pasquale, F. (2017) · Studies in big data · doi:10.1007/978-3-319-54024-5 · Cited by 61
Introducing children to machine learning concepts through hands-on experience
Hitron, T., Wald, I. Y., Erel, H., & Zuckerman, O. (2018) · ACM International Conference on Interaction Design and Children (IDC) · doi:10.1145/3202185.3210776 · Cited by 61 · cited 1×
“Besides machine learning experts, many other end users can also benefit from machine learning[41, 129], and sometimes human-machine collaborations exhibit better performance than the human or the machine alone[4, 30, 115].”
BackgroundDasgupta, A., Lee, J.-Y., Wilson, R., Lafrance, R. A., Cramer, N., Cook, K., & Payne, S. (2017) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2016.2598544 · Cited by 59 · cited 2×
“Both verbal[21, 52, 117] and visual[14, 101] explanations were shown to provide transparency[14, 52] and increase users’ trust[117].”
BackgroundMethodThe effects of metaphors on novice and expert learners' performance and mental-model development
Hsu, Y.-C. (2006) · Interacting with Computers · doi:10.1016/j.intcom.2005.10.008 · Cited by 56
Zhang, H., Hou, Y., Zhang, J., Qi, X., & Wang, F. (2014) · The International Journal of Advanced Manufacturing Technology · doi:10.1007/s00170-014-6654-1 · Cited by 52 · cited 1×
“We were aware that bar[6, 38, 57, 108] and radar[127] charts were commonly used to show features, but little evidence supports that they are more effective than rose charts[56].”
MethodTrust, Self-Confidence and Authority in Human-Machine Systems
Inagaki, T., Moray, N. P., & Itoh, M. (1998) · IFAC Proceedings Volumes · doi:10.1016/s1474-6670(17)40131-5 · Cited by 49 · cited 1×
“The accuracy of the classifier was 71%, which is of medium reliability/utility[17, 46, 60, 84, 89, 126] to foster trust in machine learning.”
BackgroundThe effects of automatic speech recognition quality on human transcription latency
Gaur, Y., Lasecki, W. S., Metze, F., & Bigham, J. P. (2016) · International Web for All Conference (W4A) · doi:10.1145/2899475.2899478 · Cited by 48 · cited 1×
“Besides machine learning experts, many other end users can also benefit from machine learning[41, 129], and sometimes human-machine collaborations exhibit better performance than the human or the machine alone[4, 30, 115].”
BackgroundWatson, M. L. (2005) · Cited by 46
Examining multiple potential models in end-user interactive concept learning
Amershi, S., Fogarty, J. A., Kapoor, A., & Tan, D. S. (2010) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/1753326.1753531 · Cited by 43 · cited 1×
“Emerging approaches explain an intelligent system’s behavior to non-technical users for debugging the system [59], improving the underlying models [2, 110], or increasing users’ trust [67].”
BackgroundMarshall, R. S. (2003) · International Business Review · doi:10.1016/s0969-5931(03)00037-4 · Cited by 30 · cited 1×
“We also ensured that the first trial was always correct to protect trust in an early stage[62, 75].”
BackgroundEffective Notification Systems Depend on User Trust.
LeeTiernan, S., Cutrell, E. B., Czerwinski, M. P., & Hoffman, H. G. (2001) · Cited by 21
Understanding Algorithms through Exploration: Supporting Knowledge Acquisition in Primary Tasks
Eiband, M., Anlauff, C., Ordenewitz, T., Zürn, M., & Hußmann, H. (2019) · Mensch und Computer (MuC) · doi:10.1145/3340764.3340772 · Cited by 8
Research works printed but not linked: 32
- Jaegul Choo and Shixia Liu . 2018. Visual Analytics for Explainable Deep Learning. arXiv preprint arXiv:1804.02527 ( 2018 ). Jaegul Choo and Shixia Liu. 2018. Visual Analytics for Explainable Deep Learning. arXiv preprint arXiv:1804.02527 (2018). · arXiv
- Sven Coppers , Jan Van den Bergh , Kris Luyten, Karin Coninx, Iulianna van der Lek-Ciudin, Tom Vanallemeersch, and Vincent Vandeghinste. 2018 . Intellingo : An Intelligible Translation Environment (CHI '18). ACM, New York, NY, USA, Article 524, 13 pages. Sven Coppers, Jan Van den Bergh, Kris Luyten, Karin Coninx, Iulianna van der Lek-Ciudin, Tom Vanallemeersch, and Vincent Vandeghinste. 2018. Intellingo: An Intelligible Translation Environment (CHI '18). ACM, New York, NY, USA, Article 524, 13 pages.
- Finale Doshi-Velez and Been Kim . 2017. Towards a rigorous science of interpretable machine learning. arXiv preprint arXiv:1702.08608 ( 2017 ). Finale Doshi-Velez and Been Kim. 2017. Towards a rigorous science of interpretable machine learning. arXiv preprint arXiv:1702.08608 (2017). · arXiv
- John Ellson , Emden Gansner , Lefteris Koutsofios , Stephen C North , and Gordon Woodhull . 2001 . Graphviz---open source graph drawing tools . In International Symposium on Graph Drawing. Springer, 483--484 . John Ellson, Emden Gansner, Lefteris Koutsofios, Stephen C North, and Gordon Woodhull. 2001. Graphviz---open source graph drawing tools. In International Symposium on Graph Drawing. Springer, 483--484.
- Amos Freedy , Ewart DeVisser , Gershon Weltman , and Nicole Coeyman . 2007 . Measurement of trust in human-robot collaboration. In Collaborative Technologies and Systems , International Symposium on. IEEE, 106--114 . Amos Freedy, Ewart DeVisser, Gershon Weltman, and Nicole Coeyman. 2007. Measurement of trust in human-robot collaboration. In Collaborative Technologies and Systems, International Symposium on. IEEE, 106--114.
- David Gefen , Elena Karahanna , and Detmar W Straub . 2003. Trust and TAM in online shopping: An integrated model. MIS quarterly 27, 1 ( 2003 ), 51--90. David Gefen, Elena Karahanna, and Detmar W Straub. 2003. Trust and TAM in online shopping: An integrated model. MIS quarterly 27, 1 (2003), 51--90.
- Ian J Goodfellow , Jonathon Shlens , and Christian Szegedy . 2014. Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572 ( 2014 ). Ian J Goodfellow, Jonathon Shlens, and Christian Szegedy. 2014. Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572 (2014). · arXiv
- David Gunning . 2017. Explainable artificial intelligence (XAI) . Defense Advanced Research Projects Agency (DARPA) , 2nd Web ( 2017 ). David Gunning. 2017. Explainable artificial intelligence (XAI). Defense Advanced Research Projects Agency (DARPA), 2nd Web (2017).
- 10.1037/0278-7393.25.4.923 · doi:10.1037/0278-7393.25.4.923 · Paper page
- Mohammad T Khasawneh , Shannon R Bowling , Xiaochun Jiang , Anand K Gramopadhye , and Brian J Melloy . 2003. A model for predicting human trust in automated systems. Origins 5 ( 2003 ). Mohammad T Khasawneh, Shannon R Bowling, Xiaochun Jiang, Anand K Gramopadhye, and Brian J Melloy. 2003. A model for predicting human trust in automated systems. Origins 5 (2003).
- Sherrie YX Komiak and Izak Benbasat . 2006. The effects of personalization and familiarity on trust and adoption of recommendation agents. MIS quarterly ( 2006 ), 941--960. Sherrie YX Komiak and Izak Benbasat. 2006. The effects of personalization and familiarity on trust and adoption of recommendation agents. MIS quarterly (2006), 941--960.
- Josua Krause , Aritra Dasgupta , Jordan Swartz , Yindalon Aphinyanaphongs , and Enrico Bertini . 2017. A workflow for visual diagnostics of binary classifiers using instance-level explanations. arXiv preprint arXiv:1705.01968 ( 2017 ). Josua Krause, Aritra Dasgupta, Jordan Swartz, Yindalon Aphinyanaphongs, and Enrico Bertini. 2017. A workflow for visual diagnostics of binary classifiers using instance-level explanations. arXiv preprint arXiv:1705.01968 (2017). · arXiv
- Josua Krause , Adam Perer , and Enrico Bertini . 2018 . A user study on the effect of aggregating explanations for interpreting machine learning models . In KDD Workshop on Interactive Data Exploration and Analytics (IDEA). Josua Krause, Adam Perer, and Enrico Bertini. 2018. A user study on the effect of aggregating explanations for interpreting machine learning models. In KDD Workshop on Interactive Data Exploration and Analytics (IDEA).
- 10.1518/hfes.46.1.50.30392 · doi:10.1518/hfes.46.1.50.30392 · Paper page
- Brian Y Lim , Qian Yang , Ashraf M Abdul , and Danding Wang . 2019 . Why these Explanations? Selecting Intelligibility Types for Explanation Goals. In IUI Workshops. Brian Y Lim, Qian Yang, Ashraf M Abdul, and Danding Wang. 2019. Why these Explanations? Selecting Intelligibility Types for Explanation Goals. In IUI Workshops.
- Maria Madsen and Shirley Gregor . 2000 . Measuring human-computer trust . In 11th Australasian Conference on Information Systems , Vol. 53 . Citeseer, 6--8. Maria Madsen and Shirley Gregor. 2000. Measuring human-computer trust. In 11th Australasian Conference on Information Systems, Vol. 53. Citeseer, 6--8.
- 10.5555/1077316.1077319 · doi:10.5555/1077316.1077319
- 10.5465/amr.1995.9508080335 · doi:10.5465/amr.1995.9508080335 · Paper page
- Maranda McBride and Shona Morgan . 2010. Trust calibration for automated decision aids . Institute for Homeland Security Solutions (2010) . Maranda McBride and Shona Morgan. 2010. Trust calibration for automated decision aids. Institute for Homeland Security Solutions (2010).
- D Harrison McKnight and Norman L Chervany . 2001. Trust and distrust definitions: One bite at a time . In Trust in Cyber-societies . Springer , 27--54. D Harrison McKnight and Norman L Chervany. 2001. Trust and distrust definitions: One bite at a time. In Trust in Cyber-societies. Springer, 27--54.
- D Harrison McKnight , Vivek Choudhury , and Charles Kacmar . 2002. Developing and validating trust measures for e-commerce: An integrative typology. Information systems research 13, 3 ( 2002 ), 334--359. D Harrison McKnight, Vivek Choudhury, and Charles Kacmar. 2002. Developing and validating trust measures for e-commerce: An integrative typology. Information systems research 13, 3 (2002), 334--359.
- David L McLain and Katarina Hackman . 1999. Trust , risk, and decision-making in organizational change. Public Administration Quarterly ( 1999 ), 152--176. David L McLain and Katarina Hackman. 1999. Trust, risk, and decision-making in organizational change. Public Administration Quarterly (1999), 152--176.
- Stephanie M Merritt , Heather Heimbaugh , Jennifer LaChapell , and Deborah Lee . 2013. I trust it, but I don't know why: Effects of implicit attitudes toward automation on trust in an automated system. Human factors 55, 3 ( 2013 ), 520--534. Stephanie M Merritt, Heather Heimbaugh, Jennifer LaChapell, and Deborah Lee. 2013. I trust it, but I don't know why: Effects of implicit attitudes toward automation on trust in an automated system. Human factors 55, 3 (2013), 520--534.
- Christopher A Miller . 2005 . Trust in adaptive automation: the role of etiquette in tuning trust via analogic and affective methods . In Proceedings of the 1st International Conference on Augmented Cognition. Citeseer, 22--27 . Christopher A Miller. 2005. Trust in adaptive automation: the role of etiquette in tuning trust via analogic and affective methods. In Proceedings of the 1st International Conference on Augmented Cognition. Citeseer, 22--27.
- Raja Parasuraman and Victor Riley . 1997. Humans and automation: Use, misuse, disuse, abuse. Human factors 39, 2 ( 1997 ), 230--253. Raja Parasuraman and Victor Riley. 1997. Humans and automation: Use, misuse, disuse, abuse. Human factors 39, 2 (1997), 230--253.
- Simone Stumpf , Adrian Bussone , and Dympna O'Sullivan . 2016. Explanations considered harmful? user interactions with machine learning systems . In Human Centred Machine Learning at CHI 2016 . Simone Stumpf, Adrian Bussone, and Dympna O'Sullivan. 2016. Explanations considered harmful? user interactions with machine learning systems. In Human Centred Machine Learning at CHI 2016.
- Sandra Wachter Brent Mittelstadt and Chris Russell. [n.d.]. Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GPDR. Harvard Journal of Law & Technology 31 2 ([n. d.]). Sandra Wachter Brent Mittelstadt and Chris Russell. [n.d.]. Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GPDR. Harvard Journal of Law & Technology 31 2 ([n. d.]).
- Dayong Wang , Aditya Khosla , Rishab Gargeya , Humayun Irshad , and Andrew H Beck . 2016. Deep learning for identifying metastatic breast cancer. arXiv preprint arXiv:1606.05718 ( 2016 ). Dayong Wang, Aditya Khosla, Rishab Gargeya, Humayun Irshad, and Andrew H Beck. 2016. Deep learning for identifying metastatic breast cancer. arXiv preprint arXiv:1606.05718 (2016). · arXiv
- 10.5555/2906831.2906852 · doi:10.5555/2906831.2906852
- Scott Cheng-Hsin Yang and Patrick Shafto . 2017 . Explainable artificial intelligence via bayesian teaching . In NIPS 2017 Workshop on Teaching Machines, Robots, and Humans. Scott Cheng-Hsin Yang and Patrick Shafto. 2017. Explainable artificial intelligence via bayesian teaching. In NIPS 2017 Workshop on Teaching Machines, Robots, and Humans.
- Jason Yosinski , Jeff Clune , Anh Nguyen , Thomas Fuchs , and Hod Lipson . 2015. Understanding neural networks through deep visualization. arXiv preprint arXiv:1506.06579 ( 2015 ). Jason Yosinski, Jeff Clune, Anh Nguyen, Thomas Fuchs, and Hod Lipson. 2015. Understanding neural networks through deep visualization. arXiv preprint arXiv:1506.06579 (2015). · arXiv
- Jason Yosinski , Jeff Clune , Anh Mai Nguyen , Thomas J. Fuchs, and Hod Lipson. 2015 . Understanding Neural Networks Through Deep Visualization. CoRR abs/1506.06579 (2015). arXiv:1506.06579 Jason Yosinski, Jeff Clune, Anh Mai Nguyen, Thomas J. Fuchs, and Hod Lipson. 2015. Understanding Neural Networks Through Deep Visualization. CoRR abs/1506.06579 (2015). arXiv:1506.06579 · arXiv
Cited by
Explainable Artificial Intelligence in education
Khosravi, H., Shum, S. B., Chen, G., Conati, C., Tsai, Y.-S., Kay, J., Knight, S., Martinez-Maldonado, R., Sadiq, S., & Gašević, D. (2022) · Computers and Education: Artificial Intelligence · doi:10.1016/j.caeai.2022.100074 · Cited by 863
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
“mes paired with importance weights [8, 21, 47, 52, 63]. On vision tasks, some work takes the demonstrate-by-example approach, i.e., by explaining an example with its closest match in the training set [48, 67]. These two methods are typically less suitable for domains involving unstructured text, as the text features a…”
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
“mes paired with importance weights [8, 21, 47, 52, 63]. On vision tasks, some work takes the demonstrate-by-example approach, i.e., by explaining an example with its closest match in the training set [48, 67]. These two methods are typically less suitable for domains involving unstructured text, as the text features a…”
Expanding Explainability: Towards Social Transparency in AI systems
Ehsan, U., Liao, Q. V., Muller, M., Riedl, M. O., & Weisz, J. D. (2021) · Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3411764.3445188 · Cited by 538
“There have been rather mixed results on whether current XAI techniques could appropriately enhance user trust [15, 80, 107] or the intended task performance, whether for decision making [12, 58, 111], model evaluation [6, 13, 22], or model development [50].”
ResultExploring students' perspectives on generative AI-assisted academic writing
Kim, J., Yu, S., Detrick, R., & Li, N. (2025) · Education and Information Technologies · doi:10.1007/s10639-024-12878-7 · Cited by 438
“…perspectives and demonstrate a range of explainable AI techniques and methodologies to better assist in sensemaking (Alqaraawi et al., 2020), enhancing user trust (Yang et al., 2020), or enabling shared decision making between student and AI system (Kim et al., 2024; Liao et al., 2020,).”
Metadata
- Authors
- Yang, F., Huang, Z., Scholtz, J., & Arendt, D. L.
- Affiliations
- Brown University (US)
- Pacific Northwest National Laboratory (US)
- Venue
- Proceedings of the 25th International Conference on Intelligent User Interfaces
- Publisher
- ACM
- Published
- 2020-03-17
- Pages
- 189-201
- OpenAlex
- W3009578469
- Cited by
- 200
- References
- 97
- Citations by year
- 2026: 21 · 2025: 29 · 2024: 56 · 2023: 34 · 2022: 25 · 2021: 30 · 2020: 4
- FWCI
- 8.87
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- ACM International Conference on Intelligent User Interfaces (IUI) (publishedVersion)
- OSF Preprints (OSF Preprints) (submittedVersion)
- 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 › Computer Graphics and Computer-Aided Design › Data Visualization and Analytics
- Keywords
- explainable machine learning, example-based explanations, trust in machine learning, spatial configuration, visual representation, performance feedback, human-machine decision-making, end users
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.