# Assessing Language Model Deployment with Risk Cards

arXiv: https://arxiv.org/abs/2303.18190 · HTML: https://mlsanity.com/paper/2303.18190/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 66 references that are in the map.
- First posted on arXiv 31 Mar 2023.

## Builds on (most cited first, 28 of 28)

- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models](https://mlsanity.com/paper/2206.04615/) (2022)
- [Datasheets for Datasets](https://mlsanity.com/paper/1803.09010/) (2018)
- [RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models](https://mlsanity.com/paper/2009.11462/) (2020)
- [Model Cards for Model Reporting](https://mlsanity.com/paper/1810.03993/) (2018)
- [Red Teaming Language Models with Language Models](https://mlsanity.com/paper/2202.03286/) (2022)
- [Ethical and social risks of harm from Language Models](https://mlsanity.com/paper/2112.04359/) (2021)
- [StereoSet: Measuring stereotypical bias in pretrained language models](https://mlsanity.com/paper/2004.09456/) (2020)
- [Adversarial NLI: A New Benchmark for Natural Language Understanding](https://mlsanity.com/paper/1910.14599/) (2019)
- [The State and Fate of Linguistic Diversity and Inclusion in the NLP World](https://mlsanity.com/paper/2004.09095/) (2020)
- [Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned](https://mlsanity.com/paper/2209.07858/) (2022)
- [CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models](https://mlsanity.com/paper/2010.00133/) (2020)
- [Release Strategies and the Social Impacts of Language Models](https://mlsanity.com/paper/1908.09203/) (2019)
- [Gender Bias in Coreference Resolution](https://mlsanity.com/paper/1804.09301/) (2018)
- [Learning from the Worst: Dynamically Generated Datasets to Improve Online Hate Detection](https://mlsanity.com/paper/2012.15761/) (2020)
- [HateCheck: Functional Tests for Hate Speech Detection Models](https://mlsanity.com/paper/2012.15606/) (2020)
- [Bias Out-of-the-Box: An Empirical Analysis of Intersectional Occupational Biases in Popular Generative Language Models](https://mlsanity.com/paper/2102.04130/) (2021)
- [Directions in Abusive Language Training Data: Garbage In, Garbage Out](https://mlsanity.com/paper/2004.01670/) (2020)
- [A Token-level Reference-free Hallucination Detection Benchmark for Free-form Text Generation](https://mlsanity.com/paper/2104.08704/) (2021)
- [Auditing large language models: a three-layered approach](https://mlsanity.com/paper/2302.08500/) (2023)
- [Beat the AI: Investigating Adversarial Human Annotation for Reading Comprehension](https://mlsanity.com/paper/2002.00293/) (2020)
- [Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Survey](https://mlsanity.com/paper/2210.07700/) (2022)
- [Machine Generated Text: A Comprehensive Survey of Threat Models and Detection Methods](https://mlsanity.com/paper/2210.07321/) (2022)
- [Towards generalisable hate speech detection: a review on obstacles and solutions](https://mlsanity.com/paper/2102.08886/) (2021)
- [Hatemoji: A Test Suite and Adversarially-Generated Dataset for Benchmarking and Detecting Emoji-based Hate](https://mlsanity.com/paper/2108.05921/) (2021)
- [Handling and Presenting Harmful Text in NLP Research](https://mlsanity.com/paper/2204.14256/) (2022)
- [Building Human Values into Recommender Systems: An Interdisciplinary Synthesis](https://mlsanity.com/paper/2207.10192/) (2022)
- [Ethics Sheets for AI Tasks](https://mlsanity.com/paper/2107.01183/) (2021)

## Built on by (most cited first, 30 of 30)

- [An Introduction to Vision-Language Modeling](https://mlsanity.com/paper/2405.17247/) (2024)
- [Can LLM-Generated Misinformation Be Detected?](https://mlsanity.com/paper/2309.13788/) (2023)
- [The Art of Saying No: Contextual Noncompliance in Language Models](https://mlsanity.com/paper/2407.12043/) (2024)
- [Frontier AI Regulation: Managing Emerging Risks to Public Safety](https://mlsanity.com/paper/2307.03718/) (2023)
- [Introducing v0.5 of the AI Safety Benchmark from MLCommons](https://mlsanity.com/paper/2404.12241/) (2024)
- [The Past, Present and Better Future of Feedback Learning in Large Language Models for Subjective Human Preferences and Values](https://mlsanity.com/paper/2310.07629/) (2023)
- [garak: A Framework for Security Probing Large Language Models](https://mlsanity.com/paper/2406.11036/) (2024)
- [Summon a Demon and Bind it: A Grounded Theory of LLM Red Teaming](https://mlsanity.com/paper/2311.06237/) (2023)
- [Adversarial Nibbler: An Open Red-Teaming Method for Identifying Diverse Harms in Text-to-Image Generation](https://mlsanity.com/paper/2403.12075/) (2024)
- [Mapping the Ethics of Generative AI: A Comprehensive Scoping Review](https://mlsanity.com/paper/2402.08323/) (2024)
- [Near to Mid-term Risks and Opportunities of Open-Source Generative AI](https://mlsanity.com/paper/2404.17047/) (2024)
- [Risks and Opportunities of Open-Source Generative AI](https://mlsanity.com/paper/2405.08597/) (2024)
- [A Security Risk Taxonomy for Prompt-Based Interaction With Large Language Models](https://mlsanity.com/paper/2311.11415/) (2023)
- [BenchmarkCards: Standardized Documentation for Large Language Model Benchmarks](https://mlsanity.com/paper/2410.12974/) (2024)
- [Seeing Seeds Beyond Weeds: Green Teaming Generative AI for Beneficial Uses](https://mlsanity.com/paper/2306.03097/) (2023)
- [Adversarial Nibbler: A Data-Centric Challenge for Improving the Safety of Text-to-Image Models](https://mlsanity.com/paper/2305.14384/) (2023)
- [Temporal Blind Spots in Large Language Models](https://mlsanity.com/paper/2401.12078/) (2024)
- [Oversight Structures for Agentic AI in Public-Sector Organizations](https://mlsanity.com/paper/2506.04836/) (2025)
- [Invisible Filters: Cultural Bias in Hiring Evaluations Using Large Language Models](https://mlsanity.com/paper/2508.16673/) (2025)
- [Regulation and NLP (RegNLP): Taming Large Language Models](https://mlsanity.com/paper/2310.05553/) (2023)
- [Unlocking Model Insights: A Dataset for Automated Model Card Generation](https://mlsanity.com/paper/2309.12616/) (2023)
- [Hacc-Man: An Arcade Game for Jailbreaking LLMs](https://mlsanity.com/paper/2405.15902/) (2024)
- [Unanswerability Evaluation for Retrieval Augmented Generation](https://mlsanity.com/paper/2412.12300/) (2024)
- [Red Teaming for Large Language Models At Scale: Tackling Hallucinations on Mathematics Tasks](https://mlsanity.com/paper/2401.00290/) (2023)
- [Promoting the Responsible Development of Speech Datasets for Mental Health and Neurological Disorders Research](https://mlsanity.com/paper/2406.04116/) (2024)
- [Understanding Gender Bias in AI-Generated Product Descriptions](https://mlsanity.com/paper/2506.05390/) (2025)
- [OneShield -- the Next Generation of LLM Guardrails](https://mlsanity.com/paper/2507.21170/) (2025)
- [Ethics Whitepaper: Whitepaper on Ethical Research into Large Language Models](https://mlsanity.com/paper/2410.19812/) (2024)
- [Documentation Practices of Artificial Intelligence](https://mlsanity.com/paper/2406.18620/) (2024)
- [Telling Speculative Stories to Help Humans Imagine the Harms of Healthcare AI](https://mlsanity.com/paper/2510.14718/) (2025)

## Abstract (arXiv)

This paper introduces RiskCards, a framework for structured assessment and documentation of risks associated with an application of language models. As with all language, text generated by language models can be harmful, or used to bring about harm. Automating language generation adds both an element of scale and also more subtle or emergent undesirable tendencies to the generated text. Prior work establishes a wide variety of language model harms to many different actors: existing taxonomies identify categories of harms posed by language models; benchmarks establish automated tests of these harms; and documentation standards for models, tasks and datasets encourage transparent reporting. However, there is no risk-centric framework for documenting the complexity of a landscape in which some risks are shared across models and contexts, while others are specific, and where certain conditions may be required for risks to manifest as harms. RiskCards address this methodological gap by providing a generic framework for assessing the use of a given language model in a given scenario. Each RiskCard makes clear the routes for the risk to manifest harm, their placement in harm taxonomies, and example prompt-output pairs. While RiskCards are designed to be open-source, dynamic and participatory, we present a "starter set" of RiskCards taken from a broad literature survey, each of which details a concrete risk presentation. Language model RiskCards initiate a community knowledge base which permits the mapping of risks and harms to a specific model or its application scenario, ultimately contributing to a better, safer and shared understanding of the risk landscape.