{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,18]],"date-time":"2026-04-18T11:29:03Z","timestamp":1776511743748,"version":"3.51.2"},"reference-count":86,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T00:00:00Z","timestamp":1773100800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"the European Union"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["MAKE"],"abstract":"<jats:p>Human\u2013AI collaboration (HAIC) increasingly mediates high-risk decisions in public and private sectors, yet many documented AI harms arise not only from model error but from breakdowns in joint human\u2013AI work: miscalibrated reliance, impaired contestability, misallocated agency, and governance opacity. Conventional explainable AI (XAI) approaches, often delivered as static one-shot artifacts, are poorly matched to these sociotechnical dynamics. This paper is a position paper arguing that explainability should be reframed as a harm-mitigation infrastructure for HAIC: an interactive, iterative capability that supports ongoing sensemaking, safe handoffs of control, governance stakeholder roles and institutional accountability. We introduce co-explainers as a conceptual framework for interactive XAI, in which explanations are co-produced through structured dialogue, feedback, and governance-aware escalation (explain \u2192 feedback \u2192 update \u2192 govern). To ground this position, we synthesize prior harm taxonomies into six HAIC-oriented harm clusters and use them as heuristic design lenses to derive cluster-specific explainability requirements, including uncertainty communication, provenance and logging, contrastive \u201cwhy\/why-not\u201d and counterfactual querying, role-sensitive justification, and recourse-oriented interaction protocols. We emphasize that co-explainers do not \u201cmitigate\u201d sociotechnical harms in isolation; rather, they provide an interface layer that makes harms more detectable, decisions more contestable, and accountability handoffs more operational under realistic constraints such as sealed models, dynamic updates, and value pluralism. We conclude with an agenda for evaluating co-explainers and aligning interactive XAI with governance frameworks in real-world HAIC deployments.<\/jats:p>","DOI":"10.3390\/make8030069","type":"journal-article","created":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T09:55:38Z","timestamp":1773136538000},"page":"69","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Co-Explainers: A Position on Interactive XAI for Human\u2013AI Collaboration as a Harm-Mitigation Infrastructure"],"prefix":"10.3390","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7283-312X","authenticated-orcid":false,"given":"Francisco","family":"Herrera","sequence":"first","affiliation":[{"name":"Department of Computer Science and Artificial Intelligence, Andalusian Institute on Data Science and Computational Intelligence (DaSCI), University of Granada, 18140 Granada, Spain"},{"name":"ADIA Lab, Abu Dhabi P.O. Box 3600, United Arab Emirates"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4494-7565","authenticated-orcid":false,"given":"Salvador","family":"Garc\u00eda","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Artificial Intelligence, Andalusian Institute on Data Science and Computational Intelligence (DaSCI), University of Granada, 18140 Granada, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mar\u00eda Jos\u00e9","family":"del Jesus","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Andalusian Institute on Data Science and Computational Intelligence (DaSCI), University of Ja\u00e9n, 23071 Ja\u00e9n, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luciano","family":"S\u00e1nchez","sequence":"additional","affiliation":[{"name":"Department of Computer Sciences, University of Oviedo, 33007 Oviedo, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marcos L\u00f3pez de","family":"Prado","sequence":"additional","affiliation":[{"name":"ADIA Lab, Abu Dhabi P.O. Box 3600, United Arab Emirates"},{"name":"School of Engineering, Cornell University, Ithaca, NY 14850, USA"},{"name":"Computational Research Department, Lawrence Berkeley National Laboratory, Berkeley, CA 94720, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,3,10]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Shelby, R., Rismani, S., Henne, K., Moon, A., Rostamzadeh, N., Nicholas, P., Yilla-Akbari, N., Gallegos, J., Smart, A., and Garcia, E. (2023, January 8\u201310). Sociotechnical harms of algorithmic systems: Scoping a taxonomy for harm reduction. Proceedings of the 2023 AAAI\/ACM Conference on AI, Ethics, and Society, Montr\u00e9al, QC, Canada.","DOI":"10.1145\/3600211.3604673"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1469","DOI":"10.1007\/s00146-024-01950-y","article-title":"The case for a broader approach to AI assurance: Addressing \u201chidden\u201d harms in the development of artificial intelligence","volume":"40","author":"Thomas","year":"2025","journal-title":"AI Soc."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1016\/j.inffus.2019.12.012","article-title":"Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI","volume":"58","author":"Arrieta","year":"2020","journal-title":"Inf. Fusion"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Carvalho Souza, M.E., Souza, M.E.D.C., and Weigang, L. (2025). Unveiling the Black Box: The Significance of XAI in Making LLMs Transparent. Authorea Prepr.","DOI":"10.22541\/au.173991264.46233479\/v1"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"103133","DOI":"10.1016\/j.inffus.2025.103133","article-title":"Reflections and attentiveness on eXplainable Artificial Intelligence (XAI). The journey ahead from criticisms to human\u2013AI collaboration","volume":"121","author":"Herrera","year":"2025","journal-title":"Inf. Fusion"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Bello, M., Bello, R., Garc\u00eda, M.M., Now\u00e9, A., Sevillano-Garc\u00eda, I., and Herrera, F. (Inf. Syst. Front., 2025). A Three-level Framework for LLM-enhanced Explainable AI: From Technical Explanations to Natural Language, Inf. Syst. Front., in press.","DOI":"10.1007\/s10796-025-10668-1"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Bo, J.Y., Pan, H., and Lim, B.Y. (2024, January 11\u201316). Incremental XAI: Memorable Understanding of AI with Incremental Explanations. Proceedings of the 2024 CHI Conference on Human Factors in Computing Systems, O\u2019ahu, HI, USA.","DOI":"10.1145\/3613904.3642689"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Bertrand, A., Viard, T., Belloum, R., Eagan, J.R., and Maxwell, W. (2023, January 23\u201328). On selective, mutable and dialogic XAI: A review of what users say about different types of interactive explanations. Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems, Hamburg, Germany.","DOI":"10.1145\/3544548.3581314"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"He, G., Aishwarya, N., and Gadiraju, U. (2025, January 24\u201327). Is Conversational XAI All You Need? Human-AI Decision Making With a Conversational XAI Assistant. Proceedings of the 30th International Conference on Intelligent User Interfaces, Cagliari, Italy.","DOI":"10.1145\/3708359.3712133"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Slattery, P., Saeri, A.K., Grundy, E.A.C., Graham, J., Noetel, M., Uuk, R., Dao, J., Pour, S., Casper, S., and Thompson, N. (2024). The AI Risk Repository: A Comprehensive Meta-Review, Database, and Taxonomy of Risks From Artificial Intelligence. arXiv.","DOI":"10.70777\/agi.v1i1.10881"},{"key":"ref_11","unstructured":"Abercrombie, G., Benbouzid, D., Giudici, P., Golpayegani, D., Hernandez, J., Noro, P., Pandit, H., Paraschou, E., Pownall, C., and Prajapati, J. (2024). A collaborative, human-centred taxonomy of ai, algorithmic, and automation harms. arXiv."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Acemoglu, D. (2021). Harms of AI, National Bureau of Economic Research. Technical report.","DOI":"10.3386\/w29247"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"254","DOI":"10.1016\/j.techfore.2016.08.019","article-title":"The future of employment: How susceptible are jobs to computerisation?","volume":"114","author":"Frey","year":"2017","journal-title":"Technol. Forecast. Soc. Chang."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"874","DOI":"10.1126\/science.adn0117","article-title":"Managing extreme AI risks amid rapid progress","volume":"384","author":"Bengio","year":"2024","journal-title":"Science"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Hendrycks, D., Mazeika, M., and Woodside, T. (2023). An Overview of Catastrophic AI Risks. arXiv.","DOI":"10.1201\/9781003530336-1"},{"key":"ref_16","unstructured":"Bostrom, N. (2014). Superintelligence: Paths, Dangers, Strategies, Oxford University Press."},{"key":"ref_17","unstructured":"Fearnley, L.C.A., Cairns, E., Stoneham, T., Ryan, P.M., Chubb, J.A., Iacovides, J., Iglesias Urrutia, C.P., Morgan, P.D.J., McDermid, J.A., and Habli, I. (2025, October 24). Risk of What? Defining Harm in the Context of AI Safety. Available online: https:\/\/eprints.whiterose.ac.uk\/id\/eprint\/223407\/."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"100652","DOI":"10.1016\/j.patter.2022.100652","article-title":"Atomist or holist? A diagnosis and vision for more productive interdisciplinary AI ethics dialogue","volume":"4","author":"Greene","year":"2023","journal-title":"Patterns"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"3015","DOI":"10.1007\/s43681-024-00622-3","article-title":"Explanation needs and ethical demands: Unpacking the instrumental value of XAI","volume":"5","author":"Alpsancar","year":"2025","journal-title":"AI Ethics"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"501","DOI":"10.1111\/jcom.12098","article-title":"Repeated Exposure to Narrative Entertainment and the Salience of Moral Intuitions","volume":"64","author":"Grizzard","year":"2014","journal-title":"J. Commun."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Kay, J., Kasirzadeh, A., and Mohamed, S. (2024, January 21\u201323). Epistemic injustice in generative AI. Proceedings of the AAAI\/ACM Conference on AI, Ethics, and Society, San Jose, CA, USA.","DOI":"10.1609\/aies.v7i1.31671"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Mollema, W.J.T. (2025). A taxonomy of epistemic injustice in the context of AI and the case for generative hermeneutical erasure. arXiv.","DOI":"10.1007\/s43681-025-00801-w"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"100140","DOI":"10.1016\/j.glmedi.2024.100140","article-title":"From scalpels to algorithms: The risk of dependence on artificial intelligence in surgery","volume":"3","author":"Adegbesan","year":"2024","journal-title":"J. Med. Surg. Public Health"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1007\/s13347-024-00762-8","article-title":"Toward an Ethics of AI Belief","volume":"37","author":"Ma","year":"2024","journal-title":"Philos. Technol."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1007\/s11023-025-09724-1","article-title":"Put it to the Test: Getting Serious About Explanation in Explainable Artificial Intelligence","volume":"35","author":"Boge","year":"2025","journal-title":"Minds Mach."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"172","DOI":"10.1038\/s42256-025-00984-1","article-title":"On the caveats of AI autophagy","volume":"7","author":"Xing","year":"2025","journal-title":"Nat. Mach. Intell."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Khozin, S. (2024). Non-Obvious Alien AI Constructions: Opportunities and Implications. Preprints.","DOI":"10.20944\/preprints202408.1929.v1"},{"key":"ref_28","unstructured":"Fazelpour, S., and Magnani, M. (2025). Aspirational Affordances of AI. arXiv."},{"key":"ref_29","unstructured":"Dohn\u00e1ny, S., Kurth-Nelson, Z., Spens, E., Luettgau, L., Reid, A., Summerfield, C., Shanahan, M., and Nour, M.M. (2025). Technological folie\u2216a deux: Feedback Loops Between AI Chatbots and Mental Illness. arXiv."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Zhang, R., Li, H., Meng, H., Zhan, J., Gan, H., and Lee, Y.C. (May, January 26). The dark side of ai companionship: A taxonomy of harmful algorithmic behaviors in human-ai relationships. Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems, Yokohama, Japan.","DOI":"10.1145\/3706598.3713429"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1038\/s42256-024-00793-y","article-title":"Mitigating allocative tradeoffs and harms in an environmental justice data tool","volume":"6","author":"Huynh","year":"2024","journal-title":"Nat. Mach. Intell."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"873","DOI":"10.1007\/s43681-024-00485-8","article-title":"AI for all: Diversity and Inclusion in AI","volume":"4","author":"Zowghi","year":"2024","journal-title":"AI Ethics"},{"key":"ref_33","unstructured":"NSPCC (2025). Viewing Generative AI and Children\u2019s Safety in the Round, NSPCC. Available online: https:\/\/learning.nspcc.org.uk\/research-resources\/2025\/generative-ai-childrens-safety."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Ibrahim, L., Huang, S., Bhatt, U., Ahmad, L., and Anderljung, M. (2024). Towards interactive evaluations for interaction harms in human-AI systems. arXiv.","DOI":"10.1609\/aies.v8i2.36631"},{"key":"ref_35","unstructured":"Bariach, B., Hogan, B., and McBride, K. (2024). Towards a harms taxonomy of ai likeness generation. arXiv."},{"key":"ref_36","unstructured":"Dogra, A., Pillutla, K., Deshpande, A., Sai, A.B., Nay, J., Rajpurohit, T., Kalyan, A., and Ravindran, B. (2024). Deception in reinforced autonomous agents. arXiv."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"100988","DOI":"10.1016\/j.patter.2024.100988","article-title":"AI deception: A survey of examples, risks, and potential solutions","volume":"5","author":"Park","year":"2024","journal-title":"Patterns"},{"key":"ref_38","unstructured":"Thomas, R., and Uminsky, D. (2020). The Problem with Metrics is a Fundamental Problem for AI. arXiv."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Choudhury, A., and Chaudhry, Z. (2024). Large Language Models and User Trust: Consequence of Self-Referential Learning Loop and the Deskilling of Healthcare Professionals. arXiv.","DOI":"10.2196\/preprints.56764"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Gunkel, D.J. (2012). The Machine Question: Critical Perspectives on AI, Robots, and Ethics, MIT Press.","DOI":"10.7551\/mitpress\/8975.001.0001"},{"key":"ref_41","unstructured":"Betley, J., Tan, D., Warncke, N., Sztyber-Betley, A., Bao, X., Soto, M., Labenz, N., and Evans, O. (2025). Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs. arXiv."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"1871","DOI":"10.1007\/s43681-024-00502-w","article-title":"Exploiting the margin: How capitalism fuels AI at the expense of minoritized groups","volume":"5","year":"2025","journal-title":"AI Ethics"},{"key":"ref_43","unstructured":"Weidinger, L., Mellor, J., Rauh, M., Griffin, C., Uesato, J., Huang, P.S., Cheng, M., Glaese, M., Balle, B., and Kasirzadeh, A. (2021). Ethical and social risks of harm from language models. arXiv."},{"key":"ref_44","first-page":"635","article-title":"Indigenous Data Sovereignty: A Catalyst for Ethical AI","volume":"64","author":"Rana","year":"2025","journal-title":"J. Bus. Ethics"},{"key":"ref_45","unstructured":"Bauer, M., Dugo, A., and Pandya, D. (2025). Breaking Barriers to Cloud Customer Choice: Unlocking Europe\u2019s AI and innovation leadership, European Centre for International Political Economy (ECIPE). Technical report."},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Birch, J. (2024). The Edge of Sentience: Risk and Precaution in Humans, Other Animals, and AI, Oxford University Press.","DOI":"10.1093\/9780191966729.001.0001"},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"867","DOI":"10.1007\/s11245-022-09874-2","article-title":"Decolonizing AI Ethics: Relational Autonomy as a Means to Counter AI Harms","volume":"42","author":"Mhlambi","year":"2023","journal-title":"Topoi"},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Mullens, D., and Shen, S. (2025). 2ACT: AI-Accentuated Career Transitions via Skill Bridges. arXiv.","DOI":"10.2139\/ssrn.5309998"},{"key":"ref_49","unstructured":"Mentxaka, O., D\u00edaz-Rodr\u00edguez, N., Coeckelbergh, M., de Prado, M.L., G\u00f3mez, E., Llorca, D.F., Herrera-Viedma, E., and Herrera, F. (2025). Aligning Trustworthy AI with Democracy: A Dual Taxonomy of Opportunities and Risks. arXiv."},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Agarwal, D., Naaman, M., and Vashistha, A. (2024). AI Suggestions Homogenize Writing Toward Western Styles and Diminish Cultural Nuances. arXiv.","DOI":"10.1145\/3706598.3713564"},{"key":"ref_51","unstructured":"P\u00f6hler, L., Schrader, V., Ladwein, A., and von Keller, F. (2024). A Technological Perspective on Misuse of Available AI. arXiv."},{"key":"ref_52","unstructured":"Wei, B., Huang, K., Huang, Y., Xie, T., Qi, X., Xia, M., Mittal, P., and Wang, M. (2024). Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications. arXiv."},{"key":"ref_53","doi-asserted-by":"crossref","unstructured":"Hutiri, W., Papakyriakopoulos, O., and Xiang, A. (2024, January 3\u20136). Not my voice! a taxonomy of ethical and safety harms of speech generators. Proceedings of the 2024 ACM Conference on Fairness, Accountability, and Transparency, Rio de Janeiro, Brazil.","DOI":"10.1145\/3630106.3658911"},{"key":"ref_54","doi-asserted-by":"crossref","unstructured":"Zhang, C., Zhou, L., Xu, X., Wu, J., and Liu, Z. (2024). Adversarial attacks of vision tasks in the past 10 years: A survey. arXiv.","DOI":"10.1145\/3743126"},{"key":"ref_55","unstructured":"Wu, H., and Cao, Y. (2025). Membership Inference Attacks on Large-Scale Models: A Survey. arXiv."},{"key":"ref_56","first-page":"1730","article-title":"Automation-Induced Complacency Potential: Mode Confusion in Level-2 Automated Vehicle Technology","volume":"66","author":"Chu","year":"2023","journal-title":"Saf. Sci."},{"key":"ref_57","doi-asserted-by":"crossref","unstructured":"Rivera, J.P., Mukobi, G., Reuel, A., Lamparth, M., Smith, C., and Schneider, J. (2024). Escalation Risks from Language Models in Military and Diplomatic Decision-Making. arXiv.","DOI":"10.1145\/3630106.3658942"},{"key":"ref_58","unstructured":"Hammond, L., Chan, A., Clifton, J., Hoelscher-Obermaier, J., Khan, A., McLean, E., Smith, C., Barfuss, W., Foerster, J., and Gaven\u010diak, T. (2025). Multi-Agent Risks from Advanced AI. arXiv."},{"key":"ref_59","first-page":"456","article-title":"The Weaponization of Artificial Intelligence in Cybersecurity: A Systematic Review","volume":"230","author":"Nobles","year":"2024","journal-title":"Procedia Comput. Sci."},{"key":"ref_60","doi-asserted-by":"crossref","unstructured":"Kasirzadeh, A. (2024). Two types of AI existential risk: Decisive and accumulative. arXiv.","DOI":"10.1007\/s11098-025-02301-3"},{"key":"ref_61","unstructured":"Grey, M., and Segerie, C.R. (2025). The AI Risk Spectrum: From Dangerous Capabilities to Existential Threats. arXiv."},{"key":"ref_62","doi-asserted-by":"crossref","first-page":"1057","DOI":"10.1007\/s13347-021-00450-x","article-title":"Four responsibility gaps with artificial intelligence: Why they matter and how to address them","volume":"34","author":"Mecacci","year":"2021","journal-title":"Philos. Technol."},{"key":"ref_63","doi-asserted-by":"crossref","unstructured":"Xiao, S., Zou, H., Zhang, A.Q., Kumar, D., Shen, H., Hong, J., and Eslami, M. (2025). What Comes After Harm? Mapping Reparative Actions in AI through Justice Frameworks. arXiv.","DOI":"10.1609\/aies.v8i3.36754"},{"key":"ref_64","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1007\/s13347-025-00862-z","article-title":"\u2018Opacity\u2019and \u2018Trust\u2019: From Concepts and Measurements to Public Policy","volume":"38","author":"Freiman","year":"2025","journal-title":"Philos. Technol."},{"key":"ref_65","doi-asserted-by":"crossref","first-page":"2853","DOI":"10.1007\/s00146-023-01777-z","article-title":"Institutionalised distrust and human oversight of artificial intelligence: Towards a democratic design of AI governance under the European Union AI Act","volume":"39","author":"Laux","year":"2024","journal-title":"AI Soc."},{"key":"ref_66","first-page":"700","article-title":"AI, Can You Hear Me? Promoting Procedural Due Process in Government Use of Artificial Intelligence Technologies","volume":"28","author":"Goodman","year":"2022","journal-title":"Richmond J. Law Technol."},{"key":"ref_67","unstructured":"Azin, M.H., and Zandhessami, H. (2025). Strategic Alignment Patterns in National AI Policies. arXiv."},{"key":"ref_68","unstructured":"Nyilasy, G., and Gangadharbatla, H. (2025). AI-washing: The Asymmetric Effects of Its Two Types on Consumer Moral Judgments. arXiv."},{"key":"ref_69","doi-asserted-by":"crossref","first-page":"31150","DOI":"10.1038\/s41598-024-82501-9","article-title":"Explainable AI improves task performance in human\u2013AI collaboration","volume":"14","author":"Senoner","year":"2024","journal-title":"Sci. Rep."},{"key":"ref_70","unstructured":"Biecek, P., and Samek, W. (2024). Explain to Question not to Justify. arXiv."},{"key":"ref_71","unstructured":"Herrera, F., and Calder\u00f3n, R. (2025). Opacity as a Feature, Not a Flaw: The LoBOX Governance Ethic for Role-Sensitive Explainability and Institutional Trust in AI. arXiv."},{"key":"ref_72","doi-asserted-by":"crossref","first-page":"435","DOI":"10.1007\/s10111-024-00765-7","article-title":"Understanding the influence of AI autonomy on AI explainability levels in human-AI teams using a mixed methods approach","volume":"26","author":"Hauptman","year":"2024","journal-title":"Cogn. Technol. Work."},{"key":"ref_73","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1057\/s41599-024-04044-8","article-title":"Trust in AI: Progress, challenges, and future directions","volume":"11","author":"Afroogh","year":"2024","journal-title":"Humanit. Soc. Sci. Commun."},{"key":"ref_74","doi-asserted-by":"crossref","first-page":"100455","DOI":"10.1016\/j.patter.2022.100455","article-title":"How transparency modulates trust in artificial intelligence","volume":"3","author":"Zerilli","year":"2022","journal-title":"Patterns"},{"key":"ref_75","unstructured":"Sharma, M., Tong, M., Korbak, T., Duvenaud, D., Askell, A., Bowman, S.R., Cheng, N., Durmus, E., Hatfield-Dodds, Z., and Johnston, S.R. (2023). Towards understanding sycophancy in language models. arXiv."},{"key":"ref_76","unstructured":"De Vynck, G., and Merrill, J.B. (The Washington Post, 2025). We Analyzed 47,000 ChatGPT Conversations. Here\u2019s What People Really Use It for, The Washington Post."},{"key":"ref_77","doi-asserted-by":"crossref","unstructured":"Miller, T. (2023, January 12\u201315). Explainable AI is dead, long live explainable AI! hypothesis-driven decision support using evaluative AI. Proceedings of the 2023 ACM Conference on Fairness, Accountability, and Transparency, Chicago, IL, USA.","DOI":"10.1145\/3593013.3594001"},{"key":"ref_78","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1007\/s11023-025-09733-0","article-title":"Hidden risks: Artificial intelligence and hermeneutic harm","volume":"35","author":"Rebera","year":"2025","journal-title":"Minds Mach."},{"key":"ref_79","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1007\/s10676-024-09800-7","article-title":"Nullius in Explanans: An ethical risk assessment for explainable AI","volume":"27","author":"Nannini","year":"2025","journal-title":"Ethics Inf. Technol."},{"key":"ref_80","first-page":"102976","article-title":"When utility meets ethics: A stakeholder perspective on agentic information systems delegation","volume":"86","author":"Saeed","year":"2026","journal-title":"Int. J. Inf. Manag."},{"key":"ref_81","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1007\/s10676-017-9430-8","article-title":"Society-in-the-loop: Programming the algorithmic social contract","volume":"20","author":"Rahwan","year":"2018","journal-title":"Ethics Inf. Technol."},{"key":"ref_82","unstructured":"Bareinboim, E. (2025, October 24). Causal Artificial Intelligence: A Roadmap for Building Causally Intelligent Systems. Draft Version (Aug 28), 2025. Available online: https:\/\/causalai-book.net\/."},{"key":"ref_83","doi-asserted-by":"crossref","unstructured":"L\u00f3pez de Prado, M. (2023). Causal Factor Investing: Can Factor Investing Become Scientific?, Cambridge University Press.","DOI":"10.1017\/9781009397315"},{"key":"ref_84","unstructured":"Hernan, M.A., and Robins, J.M.A. (2025). Causal Inference: What If, CRC press."},{"key":"ref_85","unstructured":"Wang, L., Liu, Y., and Goel, A.K. (May, January 26). \u201cGood\u201d XAI Design: For What? In Which Ways?. Proceedings of the Extended Abstracts of the CHI Conference on Human Factors in Computing Systems, Yokohama, Japan."},{"key":"ref_86","doi-asserted-by":"crossref","first-page":"4934696","DOI":"10.1155\/int\/4934696","article-title":"A Maturity Model for Practical Explainability in Artificial Intelligence-Based Applications: Integrating Analysis and Evaluation (MM4XAI-AE) Models","volume":"2025","author":"Cobos","year":"2025","journal-title":"Int. J. Intell. Syst."}],"container-title":["Machine Learning and Knowledge Extraction"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2504-4990\/8\/3\/69\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T10:24:27Z","timestamp":1773138267000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2504-4990\/8\/3\/69"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,10]]},"references-count":86,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,3]]}},"alternative-id":["make8030069"],"URL":"https:\/\/doi.org\/10.3390\/make8030069","relation":{},"ISSN":["2504-4990"],"issn-type":[{"value":"2504-4990","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,10]]}}}