Overconfidence, sycophancy and poor calibration
The system expresses unwarranted confidence, agrees with user errors (sycophancy), or is poorly calibrated, masking its unreliability.
- Risk family
- Model & system behaviour
- MIT domain
- 3. Misinformation
- MIT subdomain
- 3.1 > False or misleading information
- AI type
- GPAI
- Scope
- System
- Source standard
- MIT AI Risk Repository v4
Provenance
- Cui2024Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems02.09.05
- Gipiškis2024Risk Sources and Risk Management Measures in Support of Standards for General-Purpose AI Systems62.34.02
- Hagendorff2024Mapping the Ethics of Generative AI: A Comprehensive Scoping Review05.04.00
- Liu2024Trustworthy LLMs: A Survey and Guideline for Evaluating Large Language Models’ Alignment30.01.04 30.01.05
Ev IDs of the entries consolidated into this risk in the MIT AI Risk Repository (V4); the source sheet row appears on hover.
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.
2- A.12 ISO/IEC 23894 Annex A A.12
- A.9 ISO/IEC 23894 Annex A A.9
1- A.6.2.4 ISO/IEC 42001 Annex A A.6.2.4
More in Model & system behaviour
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.