Safe LoRA: the Silver Lining of Reducing Safety Risks when Fine-tuning Large Language Models

arXiv:2405.16833v1 Announce Type: new
Abstract: While large language models (LLMs) such as Llama-2 or GPT-4 have shown impressive zero-shot performance, fine-tuning is still necessary to enhance their performance for customized datasets, domain-specific tasks, or other private needs. However, fine-tuning all parameters of LLMs requires significant hardware resources, which can be impractical for typical users. Therefore, parameter-efficient fine-tuning such as LoRA have emerged, allowing users to fine-tune LLMs without the need for considerable computing resources, with little performance degradation compared to …

abstract arxiv cs.lg datasets domain fine-tuning gpt gpt-4 hardware however language language models large language large language models llama llms lora parameters performance risks safe safety safety risks specific tasks tasks type while zero-shot