# RiskRAG: A Data-Driven Solution for Improved AI Model Risk Reporting

arXiv: https://arxiv.org/abs/2504.08952 · HTML: https://mlsanity.com/paper/2504.08952/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Apr 2025.

## Built on by (most cited first, 9 of 9)

- [Invisible Filters: Cultural Bias in Hiring Evaluations Using Large Language Models](https://mlsanity.com/paper/2508.16673/) (2025)
- [The AI Model Risk Catalog: What Developers and Researchers Miss About Real-World AI Harms](https://mlsanity.com/paper/2508.16672/) (2025)
- [Agent-Supported Foresight for AI Systemic Risks: AI Agents for Breadth, Experts for Judgment](https://mlsanity.com/paper/2602.08565/) (2026)
- [ECHO: A Participatory Framework for Bias-Anchored AI Harm Anticipation](https://mlsanity.com/paper/2512.03068/) (2025)
- [Auto-BenchmarkCard: Automated Synthesis of Benchmark Documentation](https://mlsanity.com/paper/2512.09577/) (2025)
- [Telling Speculative Stories to Help Humans Imagine the Harms of Healthcare AI](https://mlsanity.com/paper/2510.14718/) (2025)
- [When Workout Buddies Are Virtual: AI Agents and Human Peers in a Longitudinal Physical Activity Study](https://mlsanity.com/paper/2602.01918/) (2026)
- [RiskNet: A large-scale dataset of AI risk incidents from news with alignment and multi-dimensional annotations](https://mlsanity.com/paper/2606.08376/) (2026)
- [Unaccountable Delegation, Fading Skills: Mapping the Risks of Workplace AI Agents](https://mlsanity.com/paper/2608.08601/) (2026)

## Abstract (arXiv)

Risk reporting is essential for documenting AI models, yet only 14% of model cards mention risks, out of which 96% copying content from a small set of cards, leading to a lack of actionable insights. Existing proposals for improving model cards do not resolve these issues. To address this, we introduce RiskRAG, a Retrieval Augmented Generation based risk reporting solution guided by five design requirements we identified from literature, and co-design with 16 developers: identifying diverse model-specific risks, clearly presenting and prioritizing them, contextualizing for real-world uses, and offering actionable mitigation strategies. Drawing from 450K model cards and 600 real-world incidents, RiskRAG pre-populates contextualized risk reports. A preliminary study with 50 developers showed that they preferred RiskRAG over standard model cards, as it better met all the design requirements. A final study with 38 developers, 40 designers, and 37 media professionals showed that RiskRAG improved their way of selecting the AI model for a specific application, encouraging a more careful and deliberative decision-making. The RiskRAG project page is accessible at: https://social-dynamics.net/ai-risks/card.