# The AI Model Risk Catalog: What Developers and Researchers Miss About Real-World AI Harms

arXiv: https://arxiv.org/abs/2508.16672 · HTML: https://mlsanity.com/paper/2508.16672/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 72 references that are in the map.
- First posted on arXiv 21 Aug 2025.

## Builds on (most cited first, 26 of 26)

- [Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI](https://mlsanity.com/paper/1910.10045/) (2019)
- [Model Cards for Model Reporting](https://mlsanity.com/paper/1810.03993/) (2018)
- [Ethical and social risks of harm from Language Models](https://mlsanity.com/paper/2112.04359/) (2021)
- [Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment](https://mlsanity.com/paper/2308.05374/) (2023)
- [Large Language Model as Attributed Training Data Generator: A Tale of Diversity and Bias](https://mlsanity.com/paper/2306.15895/) (2023)
- [Stable Bias: Analyzing Societal Representations in Diffusion Models](https://mlsanity.com/paper/2303.11408/) (2023)
- [A survey on datasets for fairness-aware machine learning](https://mlsanity.com/paper/2110.00530/) (2021)
- [Sociotechnical Safety Evaluation of Generative AI Systems](https://mlsanity.com/paper/2310.11986/) (2023)
- [Sociotechnical Harms of Algorithmic Systems: Scoping a Taxonomy for Harm Reduction](https://mlsanity.com/paper/2210.05791/) (2022)
- [Bias and Unfairness in Information Retrieval Systems: New Challenges in the LLM Era](https://mlsanity.com/paper/2404.11457/) (2024)
- [Preventing Repeated Real World AI Failures by Cataloging Incidents: The AI Incident Database](https://mlsanity.com/paper/2011.08512/) (2020)
- [Interactive Model Cards: A Human-Centered Approach to Model Documentation](https://mlsanity.com/paper/2205.02894/) (2022)
- [Farsight: Fostering Responsible AI Awareness During AI Application Prototyping](https://mlsanity.com/paper/2402.15350/) (2024)
- [Digital Deception: Generative Artificial Intelligence in Social Engineering and Phishing](https://mlsanity.com/paper/2310.13715/) (2023)
- [AHA!: Facilitating AI Impact Assessment by Generating Examples of Harms](https://mlsanity.com/paper/2306.03280/) (2023)
- [Lessons From Red Teaming 100 Generative AI Products](https://mlsanity.com/paper/2501.07238/) (2025)
- [Aspirations and Practice of Model Documentation: Moving the Needle with Nudging and Traceability](https://mlsanity.com/paper/2204.06425/) (2022)
- [ExploreGen: Large Language Models for Envisioning the Uses and Risks of AI Technologies](https://mlsanity.com/paper/2407.12454/) (2024)
- [AI Cards: Towards an Applied Framework for Machine-Readable AI and Risk Documentation Inspired by the EU AI Act](https://mlsanity.com/paper/2406.18211/) (2024)
- [Co-designing an AI Impact Assessment Report Template with AI Practitioners and AI Compliance Experts](https://mlsanity.com/paper/2407.17374/) (2024)
- [RiskRAG: A Data-Driven Solution for Improved AI Model Risk Reporting](https://mlsanity.com/paper/2504.08952/) (2025)
- [Atlas of AI Risks: Enhancing Public Understanding of AI Risks](https://mlsanity.com/paper/2502.05324/) (2025)
- [Social Engineering in Cybersecurity: A Domain Ontology and Knowledge Graph Application Examples](https://mlsanity.com/paper/2106.01157/) (2021)
- ["This Whole Thing Smacks of Gender": Algorithmic Exclusion in Bioimpedance-based Body Composition Analysis](https://mlsanity.com/paper/2101.08325/) (2021)
- [The Atlas of AI Incidents in Mobile Computing: Visualizing the Risks and Benefits of AI Gone Mobile](https://mlsanity.com/paper/2407.15685/) (2024)
- [Effective Mitigations for Systemic Risks from General-Purpose AI](https://mlsanity.com/paper/2412.02145/) (2024)

## Built on by (most cited first, 3 of 3)

- [Evaluation Cards: An Interpretive Layer for AI Evaluation Reporting](https://mlsanity.com/paper/2606.09809/) (2026)
- [Exploring Human Perceptions of AI Responses: Insights from a Mixed-Methods Study on Risk Mitigation in Generative Models](https://mlsanity.com/paper/2512.01892/) (2025)
- [Physiological Noise Augmentation Improves Non-Invasive Brain-to-Speech](https://mlsanity.com/paper/2607.05165/) (2026)

## Abstract (arXiv)

We analyzed nearly 460,000 AI model cards from Hugging Face to examine how developers report risks. From these, we extracted around 3,000 unique risk mentions and built the AI Model Risk Catalog. We compared these with risks identified by researchers in the MIT Risk Repository and with real-world incidents from the AI Incident Database. Developers focused on technical issues like bias and safety, while researchers emphasized broader social impacts. Both groups paid little attention to fraud and manipulation, which are common harms arising from how people interact with AI. Our findings show the need for clearer, structured risk reporting that helps developers think about human-interaction and systemic risks early in the design process. The catalog and paper appendix are available at: https://social-dynamics.net/ai-risks/catalog.