Uncensor any LLM with abliteration
✂️ What is abliteration? 💻 Implementation ⚖️ DPO Fine-Tuning Conclusion References
The third generation of Llama models provided fine-tunes (Instruct) versions that excel in understanding and following instructions. However, these models are heavily censored, designed to refuse requests seen as harmful with responses such as "As an AI assistant, I cannot help you." While this safety feature is crucial for preventing misuse, it limits the model's flexibility and responsiveness.
In this article, we will explore a technique called "abliteration" that can uncensor any LLM without retraining. This technique effectively removes the model's built-in refusal mechanism, allowing it to respond to all types of prompts.
Modern LLMs are fine-tuned for safety and instruction-following, meaning they are trained to refuse harmful requests. In their blog post, Arditi et al. have shown that this refusal behavior is mediated by a specific direction in the model's residual stream. If we prevent the model from representing this direction, it loses its ability to refuse requests. Conversely, adding this direction artificially can cause the model to refuse even harmless requests.
