Recent incidents highlight safety risks in Large Language Models (LLMs), motivating research into alignment methods like Constitutional AI (CAI). This paper explores CAI's self-critique mechanism on small, uncensored 7-9B parameter models: DeepSeek-R1-8B, Gemma-2-9B, Llama 3.1-8B, and Qwen2.5-7B. We show that while Llama-based models exhibited significant harm reduction through self-critique, other architectures demonstrated less improvement in harm detection after abliteration. These results suggest CAI's effectiveness may vary depending on model architecture and reasoning capabilities.
@article{arxiv.2503.17365,
title = {How Effective Is Constitutional AI in Small LLMs? A Study on DeepSeek-R1 and Its Peers},
author = {Antonio-Gabriel Chacón Menke and Phan Xuan Tan},
journal= {arXiv preprint arXiv:2503.17365},
year = {2025}
}