# Uncensored Open-weight Models: Redistribution as the Persistence Layer

arXiv: https://arxiv.org/abs/2609.05241 · HTML: https://mlsanity.com/paper/2609.05241/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Safety alignment, refusal and guardrails, one of 12 directions in LLM safety and security.
- Builds on 9 of its 13 references that are in the map.
- First posted on arXiv 4 Sep 2026.

## Placed in

- LLM safety and security / [Safety alignment, refusal and guardrails](https://mlsanity.com/safety/safety-alignment-refusal-and-guardrails/)

## Builds on (most cited first, 9 of 9)

- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!](https://mlsanity.com/paper/2310.03693/) (2023)
- [Refusal in Language Models Is Mediated by a Single Direction](https://mlsanity.com/paper/2406.11717/) (2024)
- [Covert Malicious Finetuning: Challenges in Safeguarding LLM Adaptation](https://mlsanity.com/paper/2406.20053/) (2024)
- [Model Merging in Pre-training of Large Language Models](https://mlsanity.com/paper/2505.12082/) (2025)
- [Malla: Demystifying Real-world Large Language Model Integrated Malicious Services](https://mlsanity.com/paper/2401.03315/) (2024)
- [Consiglieres in the Shadow: Understanding the Use of Uncensored Large Language Models in Cybercrimes](https://mlsanity.com/paper/2508.12622/) (2025)
- [Latent-space Attacks for Refusal Evasion in Language Models](https://mlsanity.com/paper/2605.21706/) (2026)

## Abstract (arXiv)

A rapidly expanding ecosystem of actors is removing built-in safety guardrails from open-weight AI models. We profile this ecosystem by identifying key producers, downstream reproductions, and emerging applications. Between January 2024 and March 2026, we identified 3,471 original uncensored models on HuggingFace, each repackaged an average of 2.4 times; three actors account for 52% of all 8,164 compressed redistributions. Once quantized and mirrored across separate accounts, formats, and registries such as Ollama, these models persist regardless of upstream removal and become easier to deploy downstream. Of the 1,643 identified GitHub applications integrating uncensored large language models (ULLMs), 25% were classified as explicitly malicious.