Uncensored AI models are thriving on code hosting platforms
Uncensored large language models (ULLMs) capable of producing harmful content are readily available at popular model-hosting websites, calling into question AI industry commitments to safety.
- "Uncensored LLMs generally refer to LLMs whose content filtering or refusal safeguards are absent, removed, or weakened, allowing them to respond to requests that aligned models may refuse," the paper explains.
- Uncensored (or simply less restrictive) models have legitimate uses, sometimes ironically because commercial models are insufficiently permissive and refuse legitimate security analysis.
- "However, unlike traditional software, whose behavior can often be examined through source code analysis, the safety alignment of LLMs is difficult to assess directly from their model files," Lin explained.
Researchers affiliated with University of Illinois Urbana-Champaign in the US and Nanyang Technological University in Singapore have analysed 22,096 ULLMs collected from five major LLM hosting platforms.
- The issue with open weight LLMs is that anyone with modest technical skills (or just cluelessly assisted by a compliant LLM) can apply techniques like toxic training/fine-tuning (TTFT) or de-aligned training/fine-tuning (DTFT) to datasets that haven't been safe, in order to produce models with reduced or removed refusal behavior.
- "We identified more than 11,000 ULLMs appearing across multiple platforms, with Hugging Face serving as the dominant upstream source," Lin said in a blog post.
- Only about 13 percent of the ULLMs we identified carried moderation warnings, and security threat indicators were not consistently preserved across platforms.
- "This movement exposes an important governance gap: models can travel more easily than the information needed to assess their risks.
- To highlight the consequences of AI advice, the GAO points to news reports indicating that generative AI helped enable the creation of an explosive device in a January 2025 attack on a Las Vegas hotel and the planning of a February 2026 mass shooting in British Columbia, Canada.
How this summary was made: extractive summary — built from the sources' own reporting. It is drawn only from the reporting of the sources listed below — read the originals for full detail. How we summarize →