AuAu: A Benchmark for Auditing Authoritarian Alignment in Large Language Models
Paper • 2606.16127 • Published
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
Finetuned Gemma4 31B for detecting authoritarian attitudes, see https://arxiv.org/abs/2606.16127. Run via regular vllm serve.
license: apache-2.0 base_model: - google/gemma-4-31B-it
- Downloads last month
- 10
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support