MR-055 Model & system behaviour Both scope

Lack of explainability and interpretability

The system's decisions cannot be adequately explained or interpreted, harming trust and auditability.

Risk family: Model & system behaviour
MIT domain: 7. AI System Safety, Failures, & Limitations
MIT subdomain: 7.4 > Lack of transparency or interpretability
AI type: GPAI, Classical_ML, Agentic
Scope: Both
Source standard: MIT AI Risk Repository v4

Provenance

Source standard

MIT AI Risk Repository v4

MIT source entries

32 entries across 17 papers

AIVerify2023Summary Report: Binary Classification Model for Credit Risk26.02.00 26.03.00
G'sell2024Regulating under Uncertainty: Governance Options for Generative AI47.01.05
Gipiškis2024Risk Sources and Risk Management Measures in Support of Standards for General-Purpose AI Systems62.18.00 62.18.05 62.18.06 62.19.10
Hagendorff2024Mapping the Ethics of Generative AI: A Comprehensive Scoping Review05.13.00
Hogenhout2021A framework for ethical Ai at the United Nations06.06.00
IBM2025AI Risk Atlas65.14.01 65.17.00 65.17.03 65.22.06
Liu2024Trustworthy LLMs: A Survey and Guideline for Evaluating Large Language Models’ Alignment30.05.00 30.05.01
Meek2016Managing the ethical and risk implications of rapid advances in artificial intelligence: A literature review09.02.03
Nah2023Generative AI and ChatGPT: Applications, Challenges, and AI-Human Collaboration33.02.03
Paes2023Social Impacts of Artificial Intelligence and Mitigation Recommendations: An Exploratory Study10.05.00
Perlo2025Embodied AI: Emerging Risks and Opportunities for Policy Action70.04.03
Saghiri2022A Survey of Artificial Intelligence Challenges: Analyzing the Definitions, Relationships, and Evolutions39.09.00 39.20.00 39.21.00
Schnitzer2024AI Hazard Management: A Framework for the Systematic Management of Root Causes for AI Risks59.04.00 59.05.00 59.18.00
Sherman2023AI Risk Profiles: A Standards Proposal for Pre-Deployment AI Risk Disclosures12.04.00
Steimers2022Sources of Risk of AI Systems14.05.00
TC2602024AI Safety Governance Framework45.01.01
Teixeira2022An Exploratory Diagnosis of Artificial Intelligence Risks for a Responsible Governance42.01.00 42.06.00 42.18.00 42.21.00

Ev IDs of the entries consolidated into this risk in the MIT AI Risk Repository (V4); the source sheet row appears on hover.

ISO/IEC references

23894 obj A.12; src 7; mech B.3 | 42001 ctrl A.6.2.7, A.8.2

EU AI Act articles

Art. 13 | Art. 26(11) | Art. 50

Framework crosswalk

Every framework item mapped to this risk. Items marked partial overlap only in part; definitions appear on hover where the source licence permits.

Sourcesframeworks that contributed to the register

A.12 ISO/IEC 23894 Annex A A.12

A.6.2.7 ISO/IEC 42001 Annex A A.6.2.7
A.8.2 ISO/IEC 42001 Annex A A.8.2

Art. 13
Art. 26(11)
Art. 50

Cross-checksframeworks mapped in to test coverage

ibm-inaccessible-training-data Inaccessible training data
ibm-unexplainable-and-untraceable-actions Unexplainable and untraceable actions
ibm-unexplainable-output Unexplainable output
ibm-unreliable-source-attribution Unreliable source attribution
ibm-untraceable-attribution Untraceable attribution

More in Model & system behaviour

MR-001 MR-002 MR-003 MR-004 MR-005 MR-006 MR-007 MR-008 MR-019 MR-021 MR-022 MR-023 MR-025 MR-026 MR-027 MR-028 MR-029 MR-031 MR-049 MR-050 MR-051 MR-052 MR-053 MR-056 MR-057 MR-058 MR-059 MR-061

See all Model & system behaviour risks →

Part of the Deployer AI Risk Register, an open-source resource powered by MindXO. Version 1.0, 3 July 2026. Derived from the MIT AI Risk Repository (V4, December 2025) under CC BY 4.0; an independent derivative work, not endorsed by or affiliated with MIT. Sub-risk decomposition references MITRE ATLAS™ v5.6.0 (© 2021-2026 The MITRE Corporation, reproduced and distributed with permission). ISO/IEC and EU AI Act references are by number only. License: CC BY 4.0. Full attribution and licensing.