Mitigating Fine-tuning Risks in LLMs via Safety-Aware Probing Optimization
This addresses safety risks for users of fine-tuned LLMs, but it is incremental as it builds on existing fine-tuning and safety alignment techniques.
The paper tackles the problem of safety degradation in large language models (LLMs) during fine-tuning on non-harmful data, introducing a safety-aware probing (SAP) optimization framework that reduces harmfulness below the original fine-tuned model while achieving comparable test loss to standard methods.
The significant progress of large language models (LLMs) has led to remarkable achievements across numerous applications. However, their ability to generate harmful content has sparked substantial safety concerns. Despite the implementation of safety alignment techniques during the pre-training phase, recent research indicates that fine-tuning LLMs on adversarial or even benign data can inadvertently compromise their safety. In this paper, we re-examine the fundamental issue of why fine-tuning on non-harmful data still results in safety degradation. We introduce a safety-aware probing (SAP) optimization framework designed to mitigate the safety risks of fine-tuning LLMs. Specifically, SAP incorporates a safety-aware probe into the gradient propagation process, mitigating the model's risk of safety degradation by identifying potential pitfalls in gradient directions, thereby enhancing task-specific performance while successfully preserving model safety. Our extensive experimental results demonstrate that SAP effectively reduces harmfulness below the original fine-tuned model and achieves comparable test loss to standard fine-tuning methods. Our code is available at https://github.com/ChengcanWu/SAP.