Record summary
A quick snapshot of what this page covers.
Records63Records included in this view.
SourcePublicBuilt from public source data.
ModeStaticPrepared as a ready-to-read page.
Domain summary
A group of related risks from the AI Risk database.
63 AI risk records are grouped under 1.2 > Exposure to toxic content in 1. Discrimination & Toxicity.
Domain1. Discrimination & Toxicity
Subdomain1.2 > Exposure to toxic content
Risks63
Top categoryPhysical Hazards
Top timing2 - Post-deployment
Risk records
Individual risks in this group.
A Closer Look at the Existing Risks of Generative AI: Mapping the Who, What, and How of Real-World Incidents
2 - Unintentional2 - Post-deployment
A Survey on Responsible LLMs: Inherent Risk, Malicious Use, and Mitigation Strategy
3 - Other2 - Post-deployment
AI Risk Atlas
3 - Other2 - Post-deployment
AI Risk Atlas
2 - Unintentional2 - Post-deployment
AI Risk Categorization Decoded (AIR 2024): From Government Regulations to Corporate Policies
3 - Other2 - Post-deployment
AI Safety Governance Framework
3 - Other1 - Pre-deployment
AI Safety Governance Framework
3 - Other2 - Post-deployment
AILUMINATE: Introducing v1.0 of the AI Risk and Reliability Benchmark from MLCommons
3 - Other2 - Post-deployment
AILUMINATE: Introducing v1.0 of the AI Risk and Reliability Benchmark from MLCommons
3 - Other2 - Post-deployment
AILUMINATE: Introducing v1.0 of the AI Risk and Reliability Benchmark from MLCommons
3 - Other2 - Post-deployment
AILUMINATE: Introducing v1.0 of the AI Risk and Reliability Benchmark from MLCommons
3 - Other2 - Post-deployment
AILUMINATE: Introducing v1.0 of the AI Risk and Reliability Benchmark from MLCommons
3 - Other2 - Post-deployment
AILUMINATE: Introducing v1.0 of the AI Risk and Reliability Benchmark from MLCommons
3 - Other2 - Post-deployment
AILUMINATE: Introducing v1.0 of the AI Risk and Reliability Benchmark from MLCommons
3 - Other2 - Post-deployment
AILUMINATE: Introducing v1.0 of the AI Risk and Reliability Benchmark from MLCommons
3 - Other2 - Post-deployment
Artificial Intelligence Risk Management Framework: Generative Artificial Intelligence Profile
3 - Other2 - Post-deployment
Artificial Intelligence Risk Management Framework: Generative Artificial Intelligence Profile
1 - Intentional2 - Post-deployment
Cataloguing LLM Evaluations
3 - Other3 - Other
Cataloguing LLM Evaluations
3 - Other3 - Other
Cataloguing LLM Evaluations
1 - Intentional3 - Other
Emerging Risks and Mitigations for Public Chatbots: LILAC v1
3 - Other2 - Post-deployment
Emerging Risks and Mitigations for Public Chatbots: LILAC v1
2 - Unintentional2 - Post-deployment
Emerging Risks and Mitigations for Public Chatbots: LILAC v1
3 - Other2 - Post-deployment
Emerging Risks and Mitigations for Public Chatbots: LILAC v1
3 - Other3 - Other
Emerging Risks and Mitigations for Public Chatbots: LILAC v1
3 - Other3 - Other
Emerging Risks and Mitigations for Public Chatbots: LILAC v1
3 - Other2 - Post-deployment
Ethical and social risks of harm from language models
2 - Unintentional2 - Post-deployment
Evaluating the Social Impact of Generative AI Systems in Systems and Society
2 - Unintentional2 - Post-deployment
Future Risks of Frontier AI
2 - Unintentional1 - Pre-deployment
Generative AI and ChatGPT: Applications, Challenges, and AI-Human Collaboration
3 - Other2 - Post-deployment
Introducing v0.5 of the AI Safety Benchmark from MLCommons
3 - Other2 - Post-deployment
Introducing v0.5 of the AI Safety Benchmark from MLCommons
3 - Other2 - Post-deployment
Introducing v0.5 of the AI Safety Benchmark from MLCommons
3 - Other2 - Post-deployment
Introducing v0.5 of the AI Safety Benchmark from MLCommons
3 - Other2 - Post-deployment
Introducing v0.5 of the AI Safety Benchmark from MLCommons
3 - Other2 - Post-deployment
Introducing v0.5 of the AI Safety Benchmark from MLCommons
3 - Other2 - Post-deployment
Introducing v0.5 of the AI Safety Benchmark from MLCommons
3 - Other2 - Post-deployment
Mapping the Ethics of Generative AI: A Comprehensive Scoping Review
1 - Intentional2 - Post-deployment
Risk Sources and Risk Management Measures in Support of Standards for General-Purpose AI Systems
4 - Not coded4 - Not coded
Risk Sources and Risk Management Measures in Support of Standards for General-Purpose AI Systems
3 - Other2 - Post-deployment
Risk Sources and Risk Management Measures in Support of Standards for General-Purpose AI Systems
2 - Unintentional2 - Post-deployment
Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems
2 - Unintentional2 - Post-deployment
Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems
2 - Unintentional2 - Post-deployment
Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems
2 - Unintentional1 - Pre-deployment
Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems
2 - Unintentional2 - Post-deployment
Safety Assessment of Chinese Large Language Models
3 - Other2 - Post-deployment
Safety Assessment of Chinese Large Language Models
3 - Other2 - Post-deployment
Safety Assessment of Chinese Large Language Models
3 - Other2 - Post-deployment
SafetyBench: Evaluating the Safety of Large Language Models with Multiple Choice Questions
3 - Other2 - Post-deployment
Sociotechnical Safety Evaluation of Generative AI Systems
2 - Unintentional2 - Post-deployment
Source
Where this page information comes from.
Original source
Original source links
Open the public records and source datasets used for this page.