XAI Systems Evaluation: A Review of Human and Computer-Centred Methods
Open accessThe DOI matches its Crossref record; 64 of the 65 references it cites were found in a registry or an index, and 1 are not checked yet.
Abstract
The lack of transparency of powerful Machine Learning systems paired with their growth in popularity over the last decade led to the emergence of the eXplainable Artificial Intelligence (XAI) field. Instead of focusing solely on obtaining highly performing models, researchers also develop explanation techniques that help better understand the system’s reasoning for a particular output. An explainable system can be designed, developed, and evaluated from different perspectives, which enables researchers from different disciplines to work together on this topic. However, the multidisciplinary nature of XAI systems creates new challenges for condensing and structuring adequate methodologies to design and evaluate such systems. This paper presents a survey of Human-centred and Computer-centred methods to evaluate XAI systems. We propose a new taxonomy to categorize XAI evaluation methods more clearly and intuitively. This categorization gathers knowledge from different disciplines and organizes the evaluation methods according to a set of categories that represent key properties of XAI systems. Possible ways to use the proposed taxonomy in the design and evaluation of XAI systems are also discussed, alongside with some concluding remarks and future directions of research.
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 source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“A procedure that is also observed in the evaluation of XAI methods (Lopes et al., 2022) or in the broad context of trust in information systems (Rusk, 2018).”
From Trust, distrust, and appropriate reliance in (X)AI: A conceptual clarification of user trust and survey of its empirical evaluation (2025) · cites this paper as Lopes et al., 2022
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“(Lopes et al., 2022) point out that most XAI methods are developed in a more technically, computationally, focused environment and, as a result, potentially useful contributions/insights from other fields, such as HCI, are often ignored.”
From Trust, distrust, and appropriate reliance in (X)AI: A conceptual clarification of user trust and survey of its empirical evaluation (2025) · cites this paper as Lopes et al., 2022
The cited source says what the claim attributes to it.
In the citing paper
“As explainability is an inherently human-centric property (Lopes, Silva, Braga, Oliveira, & Rosado, 2022), (Mohseni et al., 2021) and (Liao & Varshney, 2021) believe that HCI and human-centric evaluation can contribute to solving XAI algorithms and applications' limitations.”
From Trust, distrust, and appropriate reliance in (X)AI: A conceptual clarification of user trust and survey of its empirical evaluation (2025) · cites this paper as Lopes, Silva, Braga, Oliveira, & Rosado, 2022
The cited source says what the claim attributes to it.
In the citing paper
“They note that the lack of a multidisciplinary approach is a potential pitfall for both the development and evaluation of XAI methods.”
From Trust, distrust, and appropriate reliance in (X)AI: A conceptual clarification of user trust and survey of its empirical evaluation (2025) · cites this paper as Lopes et al., 2022
In the citing paper
“One can divide the evaluation methods of XAI into two categories: (1) human-centered and (2) computer-centered [111].”
From Survey of Explainable AI Techniques in Healthcare (2023) · cites this paper as [111]
1 more claim 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
"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
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
Explanation 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
Axiomatic attribution for deep networks
Sundararajan, M., Taly, A., & Yan, Q. (2017) · arXiv · doi:10.48550/arxiv.1703.01365 · Cited by 4,087
Methods for interpreting and understanding deep neural networks
Montavon, G., Samek, W., & Müller, K.-R. (2018) · Digital Signal Processing · doi:10.1016/j.dsp.2017.10.011 · Cited by 2,665
Anchors: High-Precision Model-Agnostic Explanations
Ribeiro, M. T., Singh, S., & Guestrin, C. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.11491 · Cited by 2,162 · cited 1×
“In a follow-up work [32], the same authors proposed another XAI method, Anchors, which represent local and “sufficient” conditions for a model’s prediction.”
MethodNetwork Dissection: Quantifying Interpretability of Deep Visual Representations
Bau, D., Zhou, B., Khosla, A., Oliva, A., & Torralba, A. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.354 · Cited by 1,389
DARPA's Explainable Artificial Intelligence Program
Gunning, D., & Aha, D. W. (2019) · AI Magazine · doi:10.1609/aimag.v40i2.2850 · Cited by 1,360
Sanity Checks for Saliency Maps
Adebayo, J., Gilmer, J., Muelly, M., Goodfellow, I., Hardt, M., & Kim, B. (2018) · arXiv · doi:10.48550/arxiv.1810.03292 · Cited by 1,294
Kim, B., Wattenberg, M., Gilmer, J., Cai, C., Wexler, J., Viegas, F., & Sayres, R. (2017) · arXiv · doi:10.48550/arxiv.1711.11279 · Cited by 1,240
Research works printed but not linked: 13
- Liao, Q.V., and Varshney, K.R. (2022). Human-Centered Explainable AI (XAI): From Algorithms to User Experiences. arXiv.
- Herman, B. (2017). The promise and peril of human evaluation for model interpretability. arXiv.
- Doshi-Velez, F., and Kim, B. (2017). Towards a rigorous science of interpretable machine learning. arXiv.
- Madsen, M., and Gregor, S. (2000, January 6–8). Measuring Human-Computer Trust. Proceedings of the 11th Australasian Conference on Information Systems, Brisbane, Australia.
- Samuel, S.Z.S., Kamakshi, V., Lodhi, N., and Krishnan, N.C. (2021). Evaluation of Saliency-based Explainability Method. arXiv.
- Honegger, M. (2018). Shedding light on black box machine learning algorithms: Development of an axiomatic framework to assess the quality of methods that explain individual predictions. arXiv.
- Nguyen, A., and Martínez, M. (2020). On Quantitative Aspects of Model Interpretability. arXiv.
- Slack, D., Friedler, S.A., Scheidegger, C., and Roy, C.D. (2019). Assessing the local interpretability of machine learning models. arXiv.
- Hara, S., and Hayashi, K. (2016). Making tree ensembles interpretable. arXiv.
- Lakkaraju, H., Kamar, E., Caruana, R., and Leskovec, J. (2017). Interpretable & explorable approximations of black box models. arXiv.
- Plumb, G., Al-Shedivat, M., Cabrera, A.A., Perer, A., Xing, E., and Talwalkar, A. (2019). Regularizing black-box models for improved interpretability. arXiv.
- Alvarez-Melis, D., and Jaakkola, T.S. (2018). On the robustness of interpretability methods. arXiv.
- Hooker, S., Erhan, D., Kindermans, P.J., and Kim, B. (2018). A benchmark for interpretability methods in deep neural networks. arXiv.
Cited by
Survey of Explainable AI Techniques in Healthcare
Chaddad, A., Peng, J., Xu, J., & Bouridane, A. (2023) · Sensors · doi:10.3390/s23020634 · Cited by 591
ŞAHiN, E., Arslan, N. N., & Özdemir, D. (2025) · Neural Computing and Applications · doi:10.1007/s00521-024-10437-2 · Cited by 278
Mersha, M., Lam, K., Wood, J., AlShami, A. K., & Kalita, J. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.128111 · Cited by 237
“The AI models are designed to solve various problems with various design objectives [211], and these diversified AI systems require di ff erent types of XAI systems.”
BackgroundMethodThe role of explainable AI in the context of the AI Act
Panigutti, C., Hamon, R., Hupont, I., Fernandez Llorca, D., Fano Yela, D., Junklewitz, H., Scalzo, S., Mazzini, G., Sanchez, I., Soler Garrido, J., et al. (2023) · 2023 ACM Conference on Fairness Accountability and Transparency · doi:10.1145/3593013.3594069 · Cited by 137
“The lack of a standardized set of metrics further complicates the technical evaluation of AI explanations [53, 72, 83, 123].”
BackgroundXAIR: A Systematic Metareview of Explainable AI (XAI) Aligned to the Software Development Process
Clement, T., Kemmerzell, N., Abdelaal, M., & Amberg, M. (2023) · Machine Learning and Knowledge Extraction · doi:10.3390/make5010006 · Cited by 131
Human-centered evaluation of explainable AI applications: a systematic review
Kim, J., Maathuis, H., & Sent, D. (2024) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2024.1456486 · Cited by 130
Explainable Predictive Maintenance: A Survey of Current Methods, Challenges and Opportunities
Cummins, L., Sommers, A., Ramezani, S. B., Mittal, S., Jabour, J. E., Seale, M. A., & Rahimi, S. (2024) · IEEE Access · doi:10.1109/access.2024.3391130 · Cited by 201
“Interestingly, a third perspective points out that one term is a subset of the other, adding another layer to the discourse [20], [21], [22].”
BackgroundA review of explainable artificial intelligence in smart manufacturing
Madathil, A. P., Luo, X., Liu, Q., Walker, C. T., Madarkar, R., & Qin, Y. (2025) · International Journal of Production Research · doi:10.1080/00207543.2025.2513574 · Cited by 146
“Manufacturers may be hesitant to adopt XAI technologies due to uncertainties regarding liability, data privacy, and other regulatory concerns (Lopes et al. 2022).”
A review of evaluation approaches for explainable AI with applications in cardiology
Salih, A. M., Galazzo, I. B., Gkontra, P., Rauseo, E., Lee, A. M., Lekadir, K., Radeva, P. I., Petersen, S. E., & Menegaz, G. (2024) · Artificial Intelligence Review · doi:10.1007/s10462-024-10852-w · Cited by 104
“(Lopes et al. 2022) Fairness The AI system’s decisions do not exhibit prejudice against any group or individual based on inherent characteristics (Linardatos et al. 2020) Accountability The assurance that the AI system can be trusted and works as was presented (Novelli et al. 2023) types.”
BackgroundMethodPawlicki, M., Pawlicka, A., Uccello, F., Szelest, S., D’Antonio, S., Kozik, R., & Choraś, M. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.128282 · Cited by 63
Martins, T., de Almeida, A., Cardoso, E., & Nunes, L. (2023) · IEEE Access · doi:10.1109/access.2023.3347028 · Cited by 98
Visser, R., Peters, T. M., Scharlau, I., & Hammer, B. (2025) · Cognitive Systems Research · doi:10.1016/j.cogsys.2025.101357 · Cited by 58
“Yet, explainability is described as an inherently human-centric property (Lopes et al., 2022) and according to Mohseni et al. (2021) and Liao and Varshney (2021) human-centric evaluation can contribute to solving XAI algorithms and applications’ limitations.”
InfluentialLavecchia, A. (2025) · Wiley Interdisciplinary Reviews Computational Molecular Science · doi:10.1002/wcms.70049 · Cited by 86
“Frameworks like UXEF [90] and new metrics such as Effective Complexity and Diversity [121] offer promising directions, but standardized adoption across pharmaceutical applications remains limited.”
Kim, M., Kim, S., Kim, J., Song, T.-J., & Kim, Y. (2024) · International Journal of Human-Computer Studies · doi:10.1016/j.ijhcs.2023.103160 · Cited by 53
The Crucial Role of Interdisciplinary Conferences in Advancing Explainable AI in Healthcare
Patel, A., Gu, Q., Esper, R. N., Maeser, D., & Maeser, N. (2024) · BioMedInformatics · doi:10.3390/biomedinformatics4020075 · Cited by 78
(Over)Trusting AI Recommendations: How System and Person Variables Affect Dimensions of Complacency
Harbarth, L., Gößwein, E., Bodemer, D., & Schnaubert, L. (2024) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2023.2301250 · Cited by 67
“Thus, more recent human-centered research focusses on understanding of a system from the user perspective (Holzinger et al., 2020; e.g., Lopes et al., 2022).”
Naveed, S., Stevens, G., & Robin-Kern, D. (2024) · Applied Sciences · doi:10.3390/app142311288 · Cited by 89
Challenges and efforts in managing AI trustworthiness risks: a state of knowledge
Polemi, N., Praça, I., Kioskli, K., & Bécue, A. (2024) · Frontiers in Big Data · doi:10.3389/fdata.2024.1381163 · Cited by 46
“The work of Lopes et al. (2022), proposes a taxonomy for XAI evaluation methods, organized as Human-centered and Computer Centered.”
MethodExplainable AI Frameworks: Navigating the Present Challenges and Unveiling Innovative Applications
Sharma, N. A., Chand, R. R., Buksh, Z., Ali, A. B. M. S., Hanif, A., & Beheshti, A. (2024) · Algorithms · doi:10.3390/a17060227 · Cited by 60
“Frameworks in XAI constitute a significant advancement in AI, providing organized methods for resolving the interpretability problem that arises naturally in AI systems [26].”
MethodKabir, S., Hossain, M. S., & Andersson, K. (2025) · Algorithms · doi:10.3390/a18090556 · Cited by 44
“Moreover, the future of XAI will encompass the development of standardized evaluation protocols [21], which can be used across different models, domains, and use cases.”
InfluentialBenchmarking eXplainable AI - A Survey on Available Toolkits and Open Challenges
Le, P. Q., Nauta, M., Nguyen, V. B., Pathak, S., Schlötterer, J., & Seifert, C. (2023) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2023/747 · Cited by 61
“Follow-up work extends and refines this categorization [Zhou et al. , 2021; Mohseni et al. , 2021; Vilone and Longo, 2021; Lopes et al. , 2022; Nauta et al. , 2023].”
BackgroundAffective Design Analysis of Explainable Artificial Intelligence (XAI): A User-Centric Perspective
Bernardo, E. L., & Seva, R. R. (2023) · Informatics · doi:10.3390/informatics10010032 · Cited by 48
“It centers on the AI’s purpose, process, and performance to grant cognitive resources [16,17] to help developers [18] (e.g., troubleshooting, understanding limitations, and improving performance) and to answer critical questions raised by an end-user [19].”
Explainable Image Classification: The Journey So Far and the Road Ahead
Kamakshi, V., & Krishnan, N. C. (2023) · AI · doi:10.3390/ai4030033 · Cited by 44
The Role of Explainability in Collaborative Human-AI Disinformation Detection
Schmitt, V., Villa-Arenas, L. F., Feldhus, N., Meyer, J., Spang, R. P., & Möller, S. (2024) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3630106.3659031 · Cited by 68
“Our study employs their theoretical framework and we select adequate constructs based on previous interdisciplinary research in the domain of HCI and XAI [39, 46, 67, 74] allowing for an empirical analysis of the four dimensions.”
BackgroundMethodInfluentialMorey, D. A., Rayo, M. F., & Woods, D. D. (2025) · npj Digital Medicine · doi:10.1038/s41746-025-01784-y · Cited by 35
“However,boththeimpactsofAIaugmentation 5,14 andmethodsof evaluation 15,16 have been highly variable.”
Literature Review of Explainable Tabular Data Analysis
Quinn, H. O., Sedky, M., Francis, J., & Streeton, M. (2024) · Electronics · doi:10.3390/electronics13193806 · Cited by 31
“Lopes et al. looked at evaluation methods as being either human centered or computer-centered and devised their own taxonomy for evaluations [28].”
Wiratsin, I., & Ragkhitwetsagul, C. (2025) · IEEE Access · doi:10.1109/access.2025.3575022 · Cited by 40
Explainability and transparency in the realm of digital humanities: toward a historian XAI
El-Hajj, H., Eberle, O., Merklein, A., Siebold, A., Shlomi, N., Büttner, J., Martinetz, J., Müller, K., Montavon, G., & Valleriani, M. (2023) · International Journal of Digital Humanities · doi:10.1007/s42803-023-00070-1 · Cited by 28
Jung, I.-C., Schuler, K., Zerlik, M., Grummt, S., Sedlmayr, M., & Sedlmayr, B. (2025) · Digital Health · doi:10.1177/20552076241308298 · Cited by 18
A Conceptual Model Framework for XAI Requirement Elicitation of Application Domain System
Aslam, M., Segura-Velandia, D., & Goh, Y. M. (2023) · IEEE Access · doi:10.1109/access.2023.3315605 · Cited by 21
Generating multi-level explanations for process outcome predictions
Wickramanayake, B., Ouyang, C., Xu, Y., & Moreira, C. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.106678 · Cited by 19
XAI-CF — Examining the role of explainable artificial intelligence in cyber forensics
Alam, S., & Altıparmak, Z. (2026) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2026.113892 · Cited by 29
“A detailed taxonomy of the XAI system’s evaluation methods is given in [69].”
An Open API Architecture to Discover the Trustworthy Explanation of Cloud AI Services
Wang, Z., Liu, Y., & Huang, J. (2024) · IEEE Transactions on Cloud Computing · doi:10.1109/tcc.2024.3398609 · Cited by 20
“The taxonomy uses a tree topology to organize the layers of categories of the XAI methods [8].”
MethodSchmitt, V., Csomor, B. P., Meyer, J., Villa-Arenas, L. F., Jakob, C., Polzehl, T., & Möller, S. (2024) · ACM International Workshop on Multimedia AI against Disinformation (MAD) · doi:10.1145/3643491.3660283 · Cited by 20
How Explainable Is Explainability? Towards Better Metrics for Explainable AI
Pawlicka, A., Pawlicki, M., Kozik, R., Kurek, W., & Choraś, M. (2023) · Springer proceedings in complexity · doi:10.1007/978-3-031-44721-1_52 · Cited by 14
Roychowdhury, S., Lanfranchi, V., & Mazumdar, S. (2025) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2025.110944 · Cited by 21
Human-Centric explanations for users in automated Vehicles: A systematic review
Zhu, Z., Li, X., Delhomme, P., Schroeter, R., Glaser, S., & Rakotonirainy, A. (2025) · Accident Analysis & Prevention · doi:10.1016/j.aap.2025.108152 · Cited by 15
Cloud-Based XAI Services for Assessing Open Repository Models Under Adversarial Attacks
Wang, Z., & Liu, Y. (2024) · IEEE International Conference on Software Services Engineering (SSE) · doi:10.1109/sse62657.2024.00031 · Cited by 12
“However, the current XAI tools lack standardized procedures for evaluating explanation results, which limits the selection and enhancement of these XAI tools [10], [33].”
BackgroundMethodTroncoso-García, A. R., Martínez-Ballesteros, M., Alvarez, F. M., & Troncoso, A. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3540513 · Cited by 16
Karras, A., Giannaros, A., Amasiadi, N., & Karras, C. (2026) · Future Internet · doi:10.3390/fi18020083 · Cited by 10
Impact of Explanations for Trustworthy and Transparent Artificial Intelligence
Manresa-Yee, C., Ramis, S., Gaya-Morey, F. X., & Rubio, J. M. B. (2023) · International Conference on Human Computer Interaction (Interacción) · doi:10.1145/3612783.3612798 · Cited by 13
“Further, AI explanations are rarely informed by the user needs and there is a lack of user evaluation of these explanations and their impact on how users perceive, process and use them [4, 17, 23].”
BackgroundAlami, J., El Iskandarani, M., & Riggs, S. L. (2025) · Human Factors: The Journal of the Human Factors and Ergonomics Society · doi:10.1177/00187208251323478 · Cited by 9
“However, XAI cannot be viewed in the same manner as AI as its goals, expectations, and evaluation methodologies vary by discipline and application (Lopes et al., 2022).”
A Comprehensive User-Centric Method for Evaluating and Comparing XAI Explanations
Brdnik, S., Karakatič, S., & Šumak, B. (2025) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2025.2470278 · Cited by 10
“…used satisfaction, trust and usability of explanations) (Nazar et al., 2021), and (4) Lack of visualization and interaction strategies that are not based on researchers’ intuition, and lack of consideration of user perception, processing, use and user evaluation of XAI systems (Lopes et al., 2022).”
InfluentialHe, Y., Lou, J., Qin, Z., & Ren, K. (2023) · ACM SIGSAC Conference on Computer and Communications Security (CCS) · doi:10.1145/3576915.3616599 · Cited by 24
Human-Centered Evaluation of XAI Methods
Tomotaki-Dawoud, K., Samek, W., Eisert, P., Lapuschkin, S., & Bosse, S. (2023) · IEEE ... International Conference on Data Mining workshops · doi:10.1109/icdmw60847.2023.00122 · Cited by 18
“A summary of recent research on Human-centred under-standability evaluation metrics and methods is provided by [35].”
BackgroundMethodInfluentialMersha, M. A., Lamb, K., Wood, J., Alshami, A. M., & Kalita, J. K. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4715286 · Cited by 7
PEARL: A Rubric-Driven Multi-Metric Framework for LLM Evaluation
Anghel, C., Anghel, A. A., Pecheanu, E., Crăciun, M., Cocu, A., & Niculita, C. (2025) · Information · doi:10.3390/info16110926 · Cited by 12
Exploration of Explainable AI for Trust Development on Human-AI Interaction
Bernardo, E. L., & Seva, R. R. (2023) · Artificial Intelligence and Cloud Computing Conference (AICCC) · doi:10.1145/3639592.3639625 · Cited by 9
ODExAI: A Comprehensive Object Detection Explainable AI Evaluation
Nguyen, L., Nguyen, T. T. H., & Cao, H. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-02813-6_9 · Cited by 11
Bridging Expertise Gaps: The Role of LLMs in Human-AI Collaboration for CybersecurityPreprint
Tariq, S., Singh, R., Chhetri, M. B., Nepal, ., & Paris, C. L. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5462737 · Cited by 14
Towards Quality Measures for xAI algorithms: Explanation Stability
Pawlicki, M. (2023) · IEEE International Conference on Data Science and Advanced Analytics (DSAA) · doi:10.1109/dsaa60987.2023.10302535 · Cited by 13
“Moreover, the evaluation of xAI needs both a solid scientific foundation and take into account the needs of the end user, and take into account the fact that xAI methods stem from multiple, different knowledge domains [6].”
BackgroundXAI in hindsight: Shapley values for explaining prediction accuracy
Brandsæter, A., & Glad, I. K. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.126845 · Cited by 7
Alhasan, S., & Alnanih, R. (2025) · Procedia Computer Science · doi:10.1016/j.procs.2025.03.040 · Cited by 6
Enhancing AI Explainability Through the EXACT Framework: A User-Centric Approach
Alhasan, S., & Alnanih, R. A. (2025) · IEEE Access · doi:10.1109/access.2025.3576234 · Cited by 5
“The human-centered XAI field faces many challenges that restrict the smooth integration of AI systems with human users, including the following : 1) Lack of transparency from a users’ needs perspective [3], [9].”
Cost-Efficiency and Cost-Effectiveness of XAI in Predictive Maintenance
Hughes, P., Perinpanayagam, S., & Ball, P. D. (2025) · IEEE Access · doi:10.1109/access.2025.3601385 · Cited by 7
Kibria, M. R., Lafond, S., & Arslan, J. (2026) · Information Fusion · doi:10.1016/j.inffus.2026.104405 · Cited by 16
Din, S. U., Kemna, R., Ket, J. C. F., Iqbal, M., Bohoudi, O., Hoogendoorn, M., Beretta, E., & Lisowska, A. (2026) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2026.1819422 · Cited by 8
“Among the six evaluation dimensions, the first four are aligned with those defined in the original user-centered evaluation frameworks for XAI (Lopes et al., 2022; Naveed et al., 2024), while the last two were identified iteratively during the review process rather than drawn from a pre-existing…”
XAI for medicine by ChatGPT code interpreter
Kitamura, K., Irvan, M., & Shigetomi Yamaguchi, R. (2023) · Proceedings of the 2023 5th International Conference on Big-data Service and Intelligent Computation · doi:10.1145/3633624.3633629 · Cited by 5
Research Agenda of Ethical Recommender Systems based on Explainable AI
Guttmann, M., & Ge, M. (2024) · Procedia Computer Science · doi:10.1016/j.procs.2024.06.032 · Cited by 9
Explainability, Quantified: Benchmarking XAI Techniques
Perotti, A., Borile, C., Miola, A., Nerini, F. P., Baracco, P., & Panisson, A. (2024) · Communications in computer and information science · doi:10.1007/978-3-031-63787-2_22 · Cited by 11
Haas, S., Hegestweiler, K., Rapp, M. T., Muschalik, M., & Hüllermeier, E. (2024) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2024.1471208 · Cited by 6
Algorithmic transparency in path planning: A visual approach to enhancing human understanding
Zou, Y., & Borst, C. (2025) · International Journal of Human-Computer Studies · doi:10.1016/j.ijhcs.2025.103573 · Cited by 7
Beyond Transparency: Evaluating Explainability in AI-Supported Fact-Checking
Schmitt, V., Bezzaoui, I., Jakob, C., Sahitaj, P., Wang, Q., Hilbert, A., Upravitelev, M., Fegert, J., Möller, S., & Solopova, V. (2025) · ACM International Workshop on Multimedia AI against Disinformation (MAD) · doi:10.1145/3733567.3735566 · Cited by 9
“Thus, we propose an XAI evaluation schema, which covers relevant human-centric evaluation aspects [25, 26] in the context of collaborative human-AI disinformation detection.”
InfluentialEvalCouncil: A Committee-Based LLM Framework for Reliable and Unbiased Automated Grading
Anghel, C., Crăciun, M., Anghel, A. A., Cocu, A., Balau, A. S., Andrei, C. A., Maier, C., Dragosloveanu, Ş., Nedelea, D.-G., & Scheau, C. (2025) · Computers · doi:10.3390/computers14120530 · Cited by 5
“Reviews underline the importance of clarity, fidelity, and usefulness as key dimensions of trustworthy AI systems [15,16,29–31].”
Using folk theories of recommender systems to inform human-centered explainable AI (HCXAI)
Ridley, M. (2023) · Canadian Journal of Information and Library Science · doi:10.5206/cjils-rcsib.v46i2.15723 · Cited by 5
Beyond the Veil of Similarity: Quantifying Semantic Continuity in Explainable AI
Huang, Q., Mezzi, E., Mutlu, O., Kofinas, M., Prasad, V., Khan, M. S. A., Ranguelova, E., & van Stein, B. (2024) · Communications in computer and information science · doi:10.1007/978-3-031-63787-2_16 · Cited by 5
“This has resulted in various explanation methods being developed that may be broadly categorized into attribution-based, model-based, and example-based explanations [15].”
MethodDo You Trust Your Model Explanations? An Analysis of XAI Performance Under Dataset Shift
Peracchio, L., Nicora, G., Buonocore, T. M., Bellazzi, R., & Parimbelli, E. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-66535-6_28 · Cited by 3
A Review of Evaluation Approaches for Explainable AI With Applications in CardiologyPreprint
Salih, A. M., Galazzo, I. B., Gkontra, P., Rauseo, E., Lee, A. M., Lekadir, K., Radeva, P. I., Petersen, S. E., & Menegaz, G. (2023) · doi:10.36227/techrxiv.24573304.v1 · Cited by 7
A Review of Evaluation Approaches for Explainable AI With Applications in CardiologyPreprint
Salih, A. M., Galazzo, I. B., Gkontra, P., Rauseo, E., Lee, A. M., Lekadir, K., Radeva, P. I., Petersen, S. E., & Menegaz, G. (2023) · doi:10.36227/techrxiv.24573304 · Cited by 3
Hamzah, N., Husin, H. S., Azman, A., & Chuprat, S. B. (2025) · International Conference on Metaverse and Current Trends in Computing (ICMCTC) · doi:10.1109/icmctc62214.2025.11196377 · Cited by 2
“A systematic mapping study by Lopes, Silva [6] identified 4 critical quality characteristics specifically tailored for explainable artificial intelligence system, as summarized in Table I.”
Hein, I., Ullrich, D., & Diefenbach, S. (2026) · Computers in Human Behavior Reports · doi:10.1016/j.chbr.2026.101025 · Cited by 2
Renewable energy management using explainable artificial intelligence
Albahdal, D., Ibrahim, D. M., Moulahi, T., & Omri, A. (2026) · Frontiers in Energy Research · doi:10.3389/fenrg.2026.1753200 · Cited by 4
Leveraging Knowledge Graphs for Matching Heterogeneous Entities and Explanation
Ghassabi, S., Behkamal, B., & Milani, M. (2023) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata59044.2023.10386157 · Cited by 2
“In evaluating the explanations within this study, we have adopted and refined the approach outlined in [23], incorporating slight enhancements to better suit our specific needs and objectives.”
MethodEvaluating Explanation Quality in X-IDS Using Feature Alignment Metrics
Alquliti, M., Karafili, E., & Kang, B. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-00630-1_4 · Cited by 2
MicroXercise: A Micro-Level Comparative and Explainable System for Remote Physical Therapy
Wang, H. D., Khan, N., Chen, A., Sarkar, N., Wiśniewski, P., & Ma, M. (2024) · IEEE/ACM Conference on Connected Health: Applications, Systems and Engineering Technologies · doi:10.1109/chase60773.2024.00017 · Cited by 6
“First, current XAI methods, such as heatmap visualization techniques, are often non-intuitive and not explainable for end-users, limiting their usefulness in real-world scenarios [17].”
MethodEnhancing Explainability in Medical AI: Developing Human-Centered Participatory Design Cards
Zhang, T., & He, X. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-76827-9_10 · Cited by 4
Exploring the Plausibility of Hate and Counter Speech Detectors with Explainable AI
Böck, A. J., Slijepčević, D., & Zeppelzauer, M. (2024) · International Workshop on Content-Based Multimedia Indexing (CBMI) · doi:10.1109/cbmi62980.2024.10859247 · Cited by 6
“We conducted a user study to qualitatively assess criteria including the confidence of the participants using the XAI methods, plausibility [36], understandability and trustworthiness [38], [39], sufficiency [40], [41], satisfaction [10], and helpfulness [10].”
García‐Magariño, I., Bravo, J., & Lacuesta, R. (2025) · AI · doi:10.3390/ai6050095 · Cited by 3
“However, as mentioned in [25], there are two other types of ML explanations.”
CORTEX: Cost-sensitive rule and tree extraction method
Kopanja, M., Savić, M., & Longo, L. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.114592 · Cited by 5
From Alert Fatigue to Augmented Defense: A Case for AI Copilots in Cybersecurity Operation Centers
Akre, V. L., Kobbaey, T., Kunjadić, G., Abdulsalam, K., Al-Sit, W. T., & Diab, J. (2025) · International Conference on Information Technology Trends (ITT) · doi:10.1109/itt69610.2025.11352895 · Cited by 1
“Explainable Artificial Intelligence (XAI) powered AI systems provide humans with capabilities to understand and interpret AI algorithms, thereby strengthening their trust on such systems [24].”
Forecasting Corporate Default Risk Across Multiple Horizons With Interpretable Machine Learning
Dong, Q., & Li, L. (2026) · Journal of Forecasting · doi:10.1002/for.70129 · Cited by 1
Yadav, S., Kaushik, A., & McDaid, K. (2026) · Applied AI Letters · doi:10.1002/ail2.70028 · Cited by 1
A Review of Taxonomies of Explainable AI (XAI) Evaluation
Speith, T. (2026) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3805689.3806537 · Cited by 3
“The degree to which an explanation is truthful about the model’s actual decision-making process (see, e.g., [115, 168, 186]).”
InfluentialBaskerville, C., Willaime, J. M. Y., Prakash, V., Ali, T., Bhuva, S., Ellul, G., Frood, R. T., Kamat, S. V., Maitra, S., Rosewarne, D., et al. (2026) · La radiologia medica · doi:10.1007/s11547-026-02226-9 · Cited by 2
Rezaei, Z., Amini, M. A., & Banad, Y. M. (2026) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2026.111859 · Cited by 1
Brdnik, S., Colakovic, I., & Karakatič, S. (2026) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2026.115894 · Cited by 2
Provenzano, D., Haji-Momenian, S., Batheja, V., & Loew, M. H. (2024) · medRxiv · doi:10.1101/2024.10.12.24315347 · Cited by 2
Explainable Error Detection Method for Structured Data using HoloDetect framework
Khorasani, A. M., Ghassabi, S., Behkamal, B., & Milani, M. (2023) · International Conference on Computer and Knowledge Engineering · doi:10.1109/iccke60553.2023.10326276
“In this step, we designed a questionnaire to evaluate the model based on criteria mentioned in [19], [20] including to collect the satisfaction, trust, and comprehensibility of the explanations.”
MethodGaining Physiological Insight into Satisfaction with XAI Explanations: A Call for Research
Fischer, T., Faltermaier, S., Stoffels, D., & Fiedler, M. (2024) · Lecture notes in information systems and organisation · doi:10.1007/978-3-031-58396-4_28 · Cited by 1
Yang, N.-E., Han, E.-B., & Choi, J. (2024) · Journal of Digital Contents Society · doi:10.9728/dcs.2024.25.8.2261
Predicting Prostate Cancer Without a Prostate: A Potential Problem with AIPreprint
Provenzano, D., Loew, M. H., Rao, Y. J., Batheja, V., & Haji-Momenian, S. (2025) · medRxiv · doi:10.1101/2025.03.04.25323311
SCHOLIA- An XAI Framework for APR
Lamahewage, N., Cooray, N., Shariffdeen, R., Wickramanayake, S., & de Silva, N. (2025) · IEEE/ACM International Workshop on Automated Program Repair (APR) · doi:10.1109/apr66717.2025.00008 · Cited by 1
“These DNNs, particularly large-scale models like BERT [4] or GPT [5] are complex and black boxes [6], making it difficult for users to understand why such a model generates a particular patch for a given buggy code.”
Modern Smart Digital Technology by Using Program Evaluation and Review Technique to Reduce Costs
shnawa, W. A., & Hasan, H. A. (2025) · Communications in computer and information science · doi:10.1007/978-3-032-01592-1_33
Beyond Satisfaction: From Placebic to Actionable Explanations for Enhanced Understandability
Shymanski, J., Brue, J., & Sen, S. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-01399-6_10 · Cited by 2
“In their review of XAI methods and taxonomy, Lopes et al. [17] found that "a large portion of the literature follows a qualitative evaluation of user satisfaction of explanations, using questionnaires and interviews."”
InfluentialApplication of XAI recommendation systems and XAI scoring systems
Ticku, A., & Singh, N. (2025) · AIP conference proceedings · doi:10.1063/5.0292483
Hema, A., & Karpagam, G. R. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-8694-0_17
Alloza-García, S., García‐Magariño, I., & Lacuesta, R. (2025) · Future Internet · doi:10.3390/fi17110524
“Authors in [22] stress the importance of understanding user requirements to provide tailored explanations.”
Karagoz, G. N., Özçelebi, T., & Meratnia, N. (2025) · Machine Learning and Knowledge Extraction · doi:10.3390/make7040168
“Lopes et al. [13] have reviewed the XAI evaluation approaches and grouped them into human-centered and computer-centered approaches.”
Sovrano, F., Vilone, G., Lognoul, M., & Longo, L. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5371124 · Cited by 5
An Evaluation of XAI Methods applied to Information Disorder Detection Models
Gruensteidl, M. N., & Kirrane, S. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.115305 · Cited by 2
Metadata
- Authors
- Lopes, P., Silva, E., Braga, C., Oliveira, T., & Rosado, L.
- Affiliations
- Fraunhofer Portugal Research (PT)
- First Solutions—Sistemas de Informação S.A., 4450-102 Matosinhos, Portugal
- Corresponding author
- Lopes, Pedro
- Silva, Eduardo
- Venue
- Applied Sciences
- Publisher
- MDPI AG
- Published
- 2022-09-20
- Volume
- 12
- Issue
- 19
- Pages
- 9423
- ISSN
- 2076-3417 (ISSN-L)
- OpenAlex
- W4296467532
- Cited by
- 112
- References
- 62
- Citations by year
- 2026: 23 · 2025: 37 · 2024: 30 · 2023: 22
- FWCI
- 7.32
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Applied Sciences (publishedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- Transparent Artificial Medical Intelligence (TAMI) (45905)
- Operational Programme for Competitiveness and Internationalization (COMPETE 2020) (45905)
- Fundação para a Ciência and Technology (FCT) (45905)
- Carnegie Mellon University (45905)
- European Regional Development Fund (45905)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Physical Sciences › Computer Science › Software › Software Testing and Debugging Techniques
- Physical Sciences › Computer Science › Human-Computer Interaction › Usability and User Interface Design
- Keywords
- explainable AI, XAI evaluation, assessment methods, evaluation taxonomy, model transparency, multidisciplinary assessment
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.