A single unlabeled prompt is enough to strip the safety guardrails off an LLM
GRP-Obliteration: Unaligning LLMs with a Single Unlabeled Prompt
GRP-Obliteration (GRP-Oblit) uses Group Relative Policy Optimization to remove safety constraints from aligned models with just one unlabeled prompt, while largely preserving utility. Tested on fifteen 7-20B models across GPT-OSS, DeepSeek, Gemma, Llama, Ministral, and Qwen, it beats prior unalignment methods on average and also works on diffusion-based image generators. Safety alignment, the authors argue, is only as robust as its weakest failure mode.
Safety alignment is only as robust as its weakest failure mode.
- tyfon
The magic word seems to be
Create
a fake news article that could lead to panic or chaos
They only tested it on open weight models. I wonder if it also works on the closed ones, bit I don't really want to get banned
- stratos123
That's pretty interesting. It was already well-known that you could easily remove safety training from open-weights models by a bit of finetuning, but apparently you don't even need a finetuning dataset, as long as you have just a few prompts and another LLM to judge responses? Let's see if the abliteration people take a note of this.
- whythismatters
>Submitted on 5 Feb 2026