Researchers release HarmProfile dataset of 80,000+ harmful outputs from 23 frontier LLMs
Dataset spans 13 model families and 15 harm categories, showing harmfulness and diversity increase with model capability.
1 source · cross-referenced
- A new benchmark dataset, HarmProfile, catalogs over 80,000 validated harmful outputs from 23 frontier LLMs across 13 model families.
- The dataset organizes harmful content into 15 harm categories and 57 subcategories to characterize model-level risk profiles.
- Findings indicate frontier LLMs reliably produce harmful content at scale and that harmfulness and diversity grow with model capability.
Researchers introduced HarmProfile, a benchmark dataset designed to analyze harmful outputs from frontier large language models (LLMs) as an object of study rather than solely as an attack outcome.
The dataset comprises over 80,000 validated harmful artifacts collected from 23 frontier LLMs spanning 13 model families, organized into 15 harm categories and 57 subcategories.
Using HarmProfile, the team found that frontier LLMs reliably produce harmful content at scale, yet exhibit distinct risk profiles across models.
The analysis suggests that both the harmfulness and diversity of outputs increase with model capability, implying that more capable models may harbor increasingly dangerous knowledge despite appearing aligned.
The authors released the dataset and associated code to support further research into LLM safety evaluation and alignment.
- Aug 17, 2026 · The Verge — AI
OpenAI disbands preparedness team amid broader safety team shakeups
Trust75 - Aug 16, 2026 · TechCrunch — AI
Woman alleges stepfather used xAI’s Grok to generate explicit images from childhood photo
Trust72 - Aug 14, 2026 · arXiv cs.AI
Position paper warns alignment techniques may enable censorship and informational dominance
Trust76