The DOI matches its Crossref record; 113 of the 122 references it cites were found in a registry or an index; 52 of the 152 sources its claims cite were checked for support.
A Review of Trustworthy and Explainable Artificial Intelligence (XAI)
Open accessAbstract
The advancement of Artificial Intelligence (AI) technology has accelerated the development of several systems that are elicited from it. This boom has made the systems vulnerable to security attacks and allows considerable bias in order to handle errors in the system. This puts humans at risk and leaves machines, robots, and data defenseless. Trustworthy AI (TAI) guarantees human value and the environment. In this paper, we present a comprehensive review of the state-of-the-art on how to build a Trustworthy and eXplainable AI, taking into account that AI is a black box with little insight into its underlying structure. The paper also discusses various TAI components, their corresponding bias, and inclinations that make the system unreliable. The study also discusses the necessity for TAI in many verticals, including banking, healthcare, autonomous system, and IoT. We unite the ways of building trust in all fragmented areas of data protection, pricing, expense, reliability, assurance, and decision-making processes utilizing TAI in several diverse industries and to differing degrees. It also emphasizes the importance of transparent and post hoc explanation models in the construction of an eXplainable AI and lists the potential drawbacks and pitfalls of building eXplainable AI. Finally, the policies for developing TAI in the autonomous vehicle construction sectors are thoroughly examined and eclectic ways of building a reliable, interpretable, eXplainable, and Trustworthy AI sys…
Overview
CoChat Summary
TL;DR
This review surveys trustworthy AI (TAI) and explainable AI (XAI), covering the European Commission’s seven TAI criteria, XAI methods, and applications in healthcare, banking/commerce, IoT, and autonomous systems. It argues that trustworthiness and explainability are increasingly necessary as AI systems become more autonomous and opaque, while identifying unresolved technical and governance challenges.
Key findings
- The paper reports that more than 70% of individuals in a cited University of Queensland study had neutral or no confidence in AI systems, leaving the total proportion of trustworthiness in AI systems at just a quarter; the public was more trusting and supportive of AI use in healthcare.
- It cites AI investment growth from $37.5 billion in 2019 to $97.9 billion in 2023, and a worldwide AI software market value of over $126 billion by 2025; in healthcare, AI is estimated to potentially address 20% of all clinical needs.
- For autonomous vehicles, the paper cites an automotive intelligent hardware/technology/operations market expanding from $1.25 billion in 2017 to $28.5 billion by 2025, and Intel’s analysis that automated cars could save 250 million hours of commuters’ annual travel time and more than 500,000 lives in the USA between 2035–2045.
- The review organizes TAI around seven EC criteria—human agency and oversight, robustness and safety, privacy and data governance, transparency, diversity and fairness, societal and environmental well-being, and accountability—and divides XAI work into transparency design and post-hoc explanation, with global and local methods.
Methods
- Design: a comprehensive narrative review/survey of TAI and XAI, not an empirical study; it synthesizes prior literature, regulations, taxonomies, and sector-specific examples.
- Data/sample: no primary dataset or experimental sample is reported; the paper draws on cited studies, EC/GDPR materials, and application examples in healthcare, banking/commerce, IoT, and autonomous systems.
- Main analysis: conceptual and taxonomic synthesis, including the seven TAI criteria, XAI categories such as transparent design versus post-hoc explanation, global versus local methods, and tables summarizing XAI research for autonomous systems.
Limitations
- The paper states that significant constraints remain: replicability of post-hoc explainability methodologies, absence of a unified understanding/criteria/metrics for interpretability, friction between efficiency and predictability, and limitations in explaining deep neural networks.
- Evident from the text: as a review, it does not report a systematic search strategy, inclusion/exclusion criteria, or quantitative meta-analysis, and it presents no primary empirical validation of the reviewed TAI/XAI approaches.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
29 Valid · 13 Not valid · 59 Not checked · 38 Own results and interpretations
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“Any errors by AI or the human involved in the creation of the AI, could lead to loss of lives [30], [33], [34].”
What the sources say
- Could not verifycites [30] [30] D. Paul, G. Sanap, S. Shenoy, D. Kalyane, K. Kalia, and R. K. Tekade, ''Artificial intelligence in drug discovery and development,'' Drug Discovery Today , vol. 26, no. 1, pp. 80-93, Jan. 2021. - sourceExperimental — accuracy not yet measured
The ‘Ongoing challenges in adopting AI’ section discusses data quality, inaccurate predictions, and the need for human intervention, but does not say that AI or human errors could cause loss of life. A further search for fatal errors, patient deaths, and related harms found no passage addressing that consequence. No page numbers were available in our copy. (LLM, conf=0.75)
- Not checked — no full text of the sourcecites [33] [33] T. Grote, ''Trustworthy medical AI systems need to know when they don't know,'' J. Med. Ethics , vol. 47, no. 5, pp. 337-338, 2021. [Online]. Available: https://jme.bmj.com/content/47/5/337 - source
- Not checked — no full text of the sourcecites [34] [34] E. J. Topol, ''High-performance medicine: The convergence of human and artificial intelligence,'' Nature Med. , vol. 25, no. 1, pp. 44-56, Jan. 2019, doi: 10.1038/s41591-018-0300-7. - source
hedgedstates a 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.
- Could not verify
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Based in the existing research summarized in Table 2, it can be concluded that XAI for autonomous systems is a catalogue of AI-driven methodologies that (1) guarantee a plausible degree of safety for a vehicle's major decisions, (2) offer rationales and accountability on the intervention choices in crucial traffic situations, and (3) follow all traffic regulations set forth by the law enforcement”
What the sources say
- Supportedcites [79] [79] S. Atakishiyev, M. Salameh, H. Yao, and R. Goebel, ''Explainable artificial intelligence for autonomous driving: A comprehensive overview and field guide for future research directions,'' 2021, arXiv:2112.11561 . - source
The proposed framework’s explanation component must justify an autonomous car’s actions and communicate that reasoning to users (framework discussion, p. 12). The survey also describes scenario-based explanations serving accountability goals (Section 4.5, p. 9), while the framework discusses timely explanations around hazardous situations and human intervention (p. 12). (LLM, conf=0.87)
- Partly supportedcites [103] [103] U. Ehsan and M. O. Riedl, ''Human-centered explainable AI: Towards a reflective sociotechnical approach,'' 2020, arXiv:2002.01092 . <!-- image --> VINAY CHAMOLA (Senior Member, IEEE) received the B.E. degree in electrical and electronics engineering and the master's degree in communication engineering from the Birla Institute of Technology and Science (BITS), Pilani, India, in 2010 and 2013, respectively, and the Ph.D. degree in electrical and computer engineering from the National University of Singapore, Singapore, in 2016. In 2015, he was a Visiting Researcher with the Autonomous Netw sourceExperimental — accuracy not yet measured
The Introduction (p. 1) defines XAI as providing human-understandable justifications, and the case study (pp. 3, 7) generates rationales for an AI agent avoiding traffic in the game Frogger. The paper mentions self-driving cars as an example of differing explanation needs (Introduction, p. 2), but does not establish that XAI provides accountability for autonomous vehicles’ intervention choices in crucial real-world traffic situations. (LLM, conf=0.86)
boostedstates 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
“Local models expressed as a sequential function of input variables can be more efficient than model simulations because limited segments of the system are more inclined to be continuous [52], [55].”
What the sources say
- Could not verifycites [52] [52] M. Nassar, K. Salah, M. H. U. Rehman, and D. Svetinovic, ''Blockchain for explainable and trustworthy artificial intelligence,'' WIREs Data Mining Knowl. Discovery , vol. 10, no. 1, pp. 1-12, Oct. 2019, doi: 10.1002/widm.1340. - sourceExperimental — accuracy not yet measured
Across the prompt passages and four further searches (local/sequential function models vs simulations; continuity of limited segments; simulation and interpolation; efficiency comparisons), our copy of Marcus (2020) never addresses local models expressed as a sequential function of input variables being cheaper than running model simulations, nor any rationale based on limited segments of a system being more continuous. The nearest material is the footnote to 2.1.5 Summary (p. 23), which speculates only that 'some low-level neural network-like computations might conceivably be more efficiently computed at a purely symbolic level', and 2.1.1 (p. 14) on operations over variables versus learned function approximation — both about symbolic vs neural implementation, not about surrogate/local models vs simulations. Since our copy does not treat the claim's point at all (and does not contradict it), attribution here cannot be checked. (LLM, conf=0.70)
- Partly supportedcites [55] [55] N. Burkart and M. F. Huber, ''A survey on the explainability of supervised machine learning,'' J. Artif. Intell. Res. , vol. 70, pp. 245-317, Jan. 2021, doi: 10.1613/jair.1.12228. - sourceExperimental — accuracy not yet measured
Section 3.2.3 (p. 11) distinguishes local surrogates, which are valid near one prediction, from global surrogates, which simulate all predictions of a black-box model. It does not say that local models are more efficient, describe them as sequential functions of input variables, or attribute an advantage to local continuity. (LLM, conf=0.80)
plainstates a 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.
- Could not verify
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Based in the existing research summarized in Table 2, it can be concluded that XAI for autonomous systems is a catalogue of AI-driven methodologies that (1) guarantee a plausible degree of safety for a vehicle's major decisions, (2) offer rationales and accountability on the intervention choices in crucial traffic situations, and (3) follow all traffic regulations set forth by the law enforcement”
What the sources say
- Partly supportedcites [79] [79] S. Atakishiyev, M. Salameh, H. Yao, and R. Goebel, ''Explainable artificial intelligence for autonomous driving: A comprehensive overview and field guide for future research directions,'' 2021, arXiv:2112.11561 . - sourceExperimental — accuracy not yet measured
Our copy supports only the general idea that regulatory compliance belongs to XAI for AVs: Section 5 (p. 11) states 'These steps are aligned with our observation regarding the role of XAI in confirming regulatory compliance', and the Conclusion (p. 15) says AVs 'need to achieve regulatory-compliant operational safety and explainability in real-time decisions'. It does not, however, define XAI as a catalogue of methodologies that 'follow all traffic regulations': Section 2.3 (p. 3) attributes law-enforcement compliance to the vehicles, noting that organizations 'proposed guidelines on the regulation of AVs to monitor their compliance with law enforcement' (NACTO, NHTSA, Transport Canada, etc.), alongside ISO 26262/21448 standards and GDPR rather than traffic regulations as such. The three-part definitional framing is the citing authors' own synthesis of their Table 2; the source supplies the compliance requirement, not the guarantee that XAI methods obey all traffic regulations. (LLM, conf=0.68)
- Could not verifycites [103] [103] U. Ehsan and M. O. Riedl, ''Human-centered explainable AI: Towards a reflective sociotechnical approach,'' 2020, arXiv:2002.01092 . <!-- image --> VINAY CHAMOLA (Senior Member, IEEE) received the B.E. degree in electrical and electronics engineering and the master's degree in communication engineering from the Birla Institute of Technology and Science (BITS), Pilani, India, in 2010 and 2013, respectively, and the Ph.D. degree in electrical and computer engineering from the National University of Singapore, Singapore, in 2016. In 2015, he was a Visiting Researcher with the Autonomous Netw sourceExperimental — accuracy not yet measured
The Introduction (pp. 1–2) defines XAI and mentions self-driving cars only as an example of differing explanation needs. The case study (p. 3) concerns an agent playing Frogger. A search for traffic regulations, law enforcement, and autonomous-vehicle compliance found no passage saying that XAI systems follow traffic laws. (LLM, conf=0.76)
boostedstates 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.
- Partly supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“The entire calculation process is transformed into a ''black box,'' which is incredibly challenging to understand [28].”
What the sources say
- Supportedcites [28] [28] R. Guidotti, A. Monreale, S. Ruggieri, F. Turini, F. Giannotti, and D. Pedreschi, ''A survey of methods for explaining black box models,'' ACM Comput. Surv. , vol. 51, no. 5, pp. 1-42, Sep. 2019, doi: 10.1145/3236009. - source
The Reverse Engineering section (p. 19) describes a black-box predictor whose inputs and outputs can be observed but whose internal workings cannot be directly seen. The Needs for Interpretable Models section (p. 3) likewise treats decisions made by black boxes as difficult to interpret. These passages support the citing sentence’s broad characterization, though “transformed” is its own metaphor. (LLM, conf=0.86)
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
28 more claims · 12 with their cited sources checked
Create a free account to see all 139 claims and to verify the 22 references still open.
- Probably not a substantial claim. 101
- It may state two separate claims as one. 36
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
“Although the black box problem presents a challenge to trusting AI by limiting our ability to understand how AI works, most AI ethicists argue that this problem can be adequately dealt with by making AI more explainable, which involves disclosing details about how an AI system operates, such as its training data, algorithms, architecture and so on31 [5, 147].”
From Autonomous artificial intelligence, scientific research, and human values (2026) · cites this paper as [147]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ D. EXPLAINABLE AI FOR AUTONOMOUS SYSTEMS · p. 18
“A semantic segmentation paradigm that is executed like a pixel-by-pixel categorization has been suggested by Hofmarcher et al. to explicate the fundamental legitimate sense of the surroundings [84].”
§ REFERENCES · p. 21
“- [84] H. He, J. Gray, A. Cangelosi, Q. Meng, T. M. McGinnity, and J. Mehnen, ''The challenges and opportunities of artificial intelligence for trustworthy robots and autonomous systems,'' in Proc. 3rd Int. Conf. Intell. Robotic Control Eng. (IRCE) , Aug. 2020, pp. 68-74.”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ I. INTRODUCTION · p. 4
“Section V sums up the challenges in current streams and highlights a perspective on achieving TAI for various organizations.”
§ V. ADVANCEMENTS AND PROGRESS OF TAI IN VARIOUS FIELDS · p. 13
“## V. ADVANCEMENTS AND PROGRESS OF TAI IN VARIOUS FIELDS”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ I. INTRODUCTION · p. 4
“future goals and needs, and how trust and explainability is the pressing priority for upcoming AI systems have been covered in Section VI, followed by the concluding remarks in Section VII.”
§ VI. CONCLUSION · p. 19
“## VI. CONCLUSION”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ D. EXPLAINABLE AI FOR AUTONOMOUS SYSTEMS · p. 18
“| [101] | 2021 | Creating causal inferences both in and out of tree-based interpretations”
§ REFERENCES · p. 21
“- [101] H. Krasowski, X. Wang, and M. Althoff, ''Safe reinforcement learning for autonomous lane changing using set-based prediction,'' in Proc. IEEE 23rd Int. Conf. Intell. Transp. Syst. (ITSC) , Sep. 2020, pp. 1-7.”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ D. EXPLAINABLE AI FOR AUTONOMOUS SYSTEMS · p. 17
“A methodology for examining how a sequence of pixel intensities influences the CNN's forecasting, called Visual-Back Propagation is presented in [94].”
§ REFERENCES · p. 21
“- [94] M. Hofmarcher, T. Unterthiner, J. Arjona-Medina, G. Klambauer, S. Hochreiter, and B. Nessler, ''Visual scene understanding for autonomous driving using semantic segmentation,'' in Explainable AI: Interpreting, Explaining and Visualizing Deep Learning . Springer, 2019, pp. 285-296.”
2 more findings
Create a free account to see every finding of this check.
Cited works that were retracted
Works this paper cites that were later retracted, from the retraction notices publishers deposit. Major when the notice came out before this paper was published.
A note, not an issue: for example, a cited work that was retracted only after this paper was published, which its authors could not have known.
In the paper
“categorization further and farther [68], [70], [71].”
Cited work 10.1155/2022/4189781 · retracted 2023-10-18 · notice 10.1155/2023/9890389 · this paper published 2023
Citations
Cites
1 retracted
U-Net-Based Medical Image Segmentation
Yin, X.-X., Sun, L., Fu, Y., Lu, R., & Zhang, Y. (2022) · Journal of Healthcare Engineering · doi:10.1155/2022/4189781 · Cited by 318 · cited 1×
“categorization further and farther [68], [70], [71].”
RetractedMastering the game of Go with deep neural networks and tree search
Silver, D., Huang, A., Maddison, C. J., Guez, A., Sifre, L., van den Driessche, G., Schrittwieser, J., Antonoglou, I., Panneershelvam, V., Lanctot, M., et al. (2016) · Nature · doi:10.1038/nature16961 · Cited by 15,612 · cited 3×
“In that tournament, Lee beat AlphaGo only once in the five matches [2].”
BackgroundLearning Deep Features for Discriminative Localization
Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., & Torralba, A. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.319 · Cited by 11,428 · cited 1×
“In reality, it’s worth emphasizing that such a form of rationalization is applicable to a wide range of autonomous system scenarios [79], [91].”
BackgroundArrieta, A. B., Díaz-Rodríguez, N., Del Ser, J., Bennetot, A., Tabik, S., Barbado, A., García, S., Gil-López, S., Molina, D., Benjamins, R., et al. (2019) · arXiv · doi:10.48550/arxiv.1910.10045 · Cited by 11,321
High-performance medicine: the convergence of human and artificial intelligence
Topol, E. J. (2019) · Nature Medicine · doi:10.1038/s41591-018-0300-7 · Cited by 10,450 · cited 2×
“Any errors by AI or the human involved in the creation of the AI, could lead to loss of lives [30], [33], [34].”
BackgroundBarredo Arrieta, A., Díaz-Rodríguez, N., Del Ser, J., Bennetot, A., Tabik, S., Barbado, A., Garcia, S., Gil-Lopez, S., Molina, D., Benjamins, R., et al. (2020) · Information Fusion · doi:10.1016/j.inffus.2019.12.012 · Cited by 10,423 · cited 2×
“The transparency structure divulges how a model functions [48], [49].”
BackgroundPeeking 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 · cited 5×
“…that categorise instances based on certain measure of similarity (such as K-nearest neighbours, K-means, and SVM), as the methodology is intuitive: locate the datum that would be the most parallel to the one presumed, and allocate the aforementioned to the very same category as the latter [48].”
BackgroundMethodInfluentialMachine learning: Algorithms, real-world applications and research directions
Sarker, I. H. (2021) · SN Computer Science · doi:10.1007/s42979-021-00592-x · Cited by 5,583 · cited 1×
“now is highly unjust and excessive [8].”
Lipton, Z. C. (2018) · Queue · doi:10.1145/3236386.3241340 · Cited by 5,427 · cited 1×
“Furthermore, the controllers facilitate widespread adoption sans jeopardizing the terminal interface, which will boost efficiency and productivity [62], [63].”
BackgroundImage segmentation using deep learning: A survey
Minaee, S., Boykov, Y. Y., Porikli, F., Plaza, A. J., Kehtarnavaz, N., & Terzopoulos, D. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3059968 · Cited by 3,796 · cited 2×
“Zhou et al. presented U-Net ++ , a new, broader neural net topology for image processing, to take categorization further and farther [68], [70], [71].”
Background
Research works printed but not linked: 5
- hoos, 2018, Automated artificial intelligence (AutoAI)
- 2019, What is GDPR the EU’s new data protection law?
- 2023, GDPR Articles and Recitals
- dastani, 2021, Responsibility Research for Trustworthy Autonomous Systems (Blue Sky Ideas Track)
- stierle, 2021, Bringing light into the darkness—A systematic literature review on explainable predictive business process monitoring techniques
Cited by
Mersha, M., Lam, K., Wood, J., AlShami, A. K., & Kalita, J. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.128111 · Cited by 237
“…in reinforcement learning is crucial, particularly for safety-critical domains, due to the need for trust, safety assurance, regulatory compliance, ethical decision-making, model debugging, collaborative human-AI interaction, accountability, and AI model adoption and acceptance [73, 81, 82].”
BackgroundMathew, D. E., Ebem, D. U., Ikegwu, A. C., Ukeoma, P. E., & Dibiaezue, N. F. (2025) · Neural Processing Letters · doi:10.1007/s11063-025-11732-2 · Cited by 168
“Furthermore, Chamola, et al. [25] reviewed that ensuring that XAI methods effectively handle real-world scenarios, including unforeseen situations and adversarial attacks, is essential for their practical applicability, and overcoming these challenges is imperative for the widespread adoption of…”
Wani, N. A., Kumar, R., Mamta, Bedi, J., & Rida, I. (2024) · Information Fusion · doi:10.1016/j.inffus.2024.102472 · Cited by 191
Douaioui, K., Oucheikh, R., Benmoussa, O., & Mabrouki, C. (2024) · Applied System Innovation · doi:10.3390/asi7050093 · Cited by 252
“Explainable AI (XAI) is becoming increasingly important to address the challenge of interpretability by emphasizing transparency in decision-making processes alongside model accuracy [41,42].”
Shadi, M. R., Mirshekali, H., & Shaker, H. R. (2025) · Renewable and Sustainable Energy Reviews · doi:10.1016/j.rser.2025.115668 · Cited by 161
Metadata
- Authors
- Chamola, V., Hassija, V., Sulthana, A. R., Ghosh, D., Dhingra, D., & Sikdar, B.
- Affiliations
- Birla Institute of Technology and Science, Pilani (IN)
- National University of Singapore (SG)
- University of Greenwich (GB)
- Jaypee Institute of Information Technology (IN)
- Venue
- IEEE Access
- Published
- 2023
- Volume
- 11
- Pages
- 78994-79015
- ISSN
- 2169-3536 (ISSN-L)
- OpenAlex
- W4385059984
- Cited by
- 352
- References
- 122
- Citations by year
- 2026: 127 · 2025: 143 · 2024: 76 · 2023: 6
- FWCI
- 33.09
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- IEEE Access (publishedVersion, cc-by-nc-nd)
- Greenwich Academic Literature Archive (University of Greenwich) (acceptedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- Ministry of Education, Singapore (A-0009040-00-00, A-0009040-01-00)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Physical Sciences › Computer Science › Artificial Intelligence › Ethics and Social Impacts of AI
- Physical Sciences › Engineering › Safety, Risk, Reliability and Quality › Safety Systems Engineering in Autonomy
- Keywords
- trustworthy AI, explainable AI, algorithmic bias, black-box models, post-hoc explanation, interpretability, autonomous vehicles, AI security, artificial intelligence in banking, artificial intelligence in healthcare, Internet of Things, AI policy
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 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol and qwen3.8-omni-flash).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: A Review of Trustworthy and Explainable Artificial Intelligence (XAI). https://app.cochat.ai/papers/10.1109/access.2023.3294569
- The paper
- Chamola, V., Hassija, V., Sulthana, A. R., Ghosh, D., Dhingra, D., & Sikdar, B. (2023). A Review of Trustworthy and Explainable Artificial Intelligence (XAI). IEEE Access. https://doi.org/10.1109/access.2023.3294569
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.