MR-051 Model & system behaviour System scope

Ethical or value misalignment in outputs and decisions

The system makes or endorses decisions that violate ethical norms or human values it should respect.

Risk family: Model & system behaviour
MIT domain: 7. AI System Safety, Failures, & Limitations
MIT subdomain: 7.3 > Lack of capability or robustness
AI type: GPAI, Agentic
Scope: System
Source standard: MIT AI Risk Repository v4

Provenance

Source standard

MIT AI Risk Repository v4

MIT source entries

34 entries across 20 papers

Abercrombie2024A Collaborative, Human-Centred Taxonomy of AI, Algorithmic, and Automation Harms58.07.01
Deng2023Towards Safer Generative Language Models: A Survey on Safety Risks, Evaluations, and Improvements04.03.00
DSIT2023Capabilities and Risks from Frontier AI67.01.00
G'sell2024Regulating under Uncertainty: Governance Options for Generative AI47.02.00
Giarmoleo2024What Ethics Can Say on Artificial Intelligence: Insights from a Systematic Literature Review37.02.04 37.02.05
IBM2025AI Risk Atlas65.07.00 65.07.01 65.15.00
InfoComm2023Cataloguing LLM Evaluations43.01.03
Kumar2023Ethical Issues in the Development of Artificial Intelligence: Recognizing the Risks38.03.00 38.05.00
Leech2024Ten Hard Problems in Artificial Intelligence We Must Get Right54.01.00
Li2025A Closer Look at the Existing Risks of Generative AI: Mapping the Who, What, and How of Real-World Incidents66.04.02
McLean2023The risks associated with Artificial General Intelligence: A systematic review08.04.00
Meek2016Managing the ethical and risk implications of rapid advances in artificial intelligence: A literature review09.06.02
Saghiri2022A Survey of Artificial Intelligence Challenges: Analyzing the Definitions, Relationships, and Evolutions39.16.00 39.19.00 39.28.00
Sun2023Safety Assessment of Chinese Large Language Models27.01.08
Teixeira2022An Exploratory Diagnosis of Artificial Intelligence Risks for a Responsible Governance42.11.00 42.17.00 42.19.00 42.20.00
Uuk2025A Taxonomy of Systemic Risks from General-Purpose AI61.02.32
Wang2025A Survey on Responsible LLMs: Inherent Risk, Malicious Use, and Mitigation Strategy74.01.07
Wirtz2020The Dark Sides of Artificial Intelligence: An Integrated AI Governance Framework for Public Administration20.02.00 20.02.02 20.02.03
Wirtz2022Governance of artificial intelligence: A risk and guideline-based integrative framework19.05.01 19.05.03 19.05.04 19.05.05
Zhang2023SafetyBench: Evaluating the Safety of Large Language Models with Multiple Choice Questions28.06.00

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.2; src 2 | 42001 ctrl A.6.1.2, A.5.4

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.2 ISO/IEC 23894 Annex A A.2

A.5.4 ISO/IEC 42001 Annex A A.5.4
A.6.1.2 ISO/IEC 42001 Annex A A.6.1.2

Cross-checksframeworks mapped in to test coverage

ibm-misaligned-actions Misaligned actions

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-052 MR-053 MR-055 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.