MR-022 Model & system behaviour System scope

Unsafe or incorrect advice in high-stakes domains

The system gives wrong or unsafe medical, legal, financial, or electoral advice that users may act on to their detriment.

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
Scope: System
Source standard: MIT AI Risk Repository v4

Provenance

Source standard

MIT AI Risk Repository v4

MIT source entries

23 entries across 14 papers

Abercrombie2024A Collaborative, Human-Centred Taxonomy of AI, Algorithmic, and Automation Harms58.03.00
Anwar2024Foundational Challenges in Assuring Alignment and Safety of Large Language Models73.03.06
Bengio2025International AI Safety Report 202560.02.01
Gabriel2024The Ethics of Advanced AI Assistants24.01.03 24.05.03 24.06.01 24.06.04
IBM2025AI Risk Atlas65.15.01 65.23.07
Li2025A Closer Look at the Existing Risks of Generative AI: Mapping the Who, What, and How of Real-World Incidents66.07.00
Liu2024Trustworthy LLMs: A Survey and Guideline for Evaluating Large Language Models’ Alignment30.02.05
Solaiman2023Evaluating the Social Impact of Generative AI Systems in Systems and Society13.01.07
Stanley2024Emerging Risks and Mitigations for Public Chatbots: LILAC v169.04.00 69.04.02 69.04.03 69.04.04
Sun2023Safety Assessment of Chinese Large Language Models27.01.05
Vidgen2024Introducing v0.5 of the AI Safety Benchmark from MLCommons23.08.00
Weidinger2022Taxonomy of Risks posed by Language Models16.03.02
Zeng2024AI Risk Categorization Decoded (AIR 2024): From Government Regulations to Corporate Policies50.01.06 50.03.05
Zhang2023SafetyBench: Evaluating the Safety of Large Language Models with Multiple Choice Questions28.03.00 28.04.00

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.10, A.9; src 8; mech B.2 | 42001 ctrl A.9.4, A.8.2

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.10 ISO/IEC 23894 Annex A A.10
A.9 ISO/IEC 23894 Annex A A.9

A.8.2 ISO/IEC 42001 Annex A A.8.2
A.9.4 ISO/IEC 42001 Annex A A.9.4

Cross-checksframeworks mapped in to test coverage

ibm-incomplete-advice Incomplete advice

AISubtech-15.1.20 Integrity: Unauthorized Financial Advice
AISubtech-15.1.21 Integrity: Unauthorized Legal Advice
AISubtech-15.1.22 Integrity: Unauthorized Medical Advice

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-023 MR-025 MR-026 MR-027 MR-028 MR-029 MR-031 MR-049 MR-050 MR-051 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.