Matching Pairs: Attributing Fine-Tuned Models to their Pre-Trained Large Language Models

conf_acl(2023)

引用 3|浏览46
暂无评分
摘要
The wide applicability and adaptability of generative large language models (LLMs) has enabled their rapid adoption. While the pre-trained models can perform many tasks, such models are often fine-tuned to improve their performance on various downstream applications. However, this leads to issues over violation of model licenses, model theft, and copyright infringement. Moreover, recent advances show that generative technology is capable of producing harmful content which exacerbates the problems of accountability within model supply chains. Thus, we need a method to investigate how a model was trained or a piece of text was generated and what their pre-trained base model was. In this paper we take the first step to address this open problem by tracing back the origin of a given fine-tuned LLM to its corresponding pre-trained base model. We consider different knowledge levels and attribution strategies, and find that we can correctly trace back 8 out of the 10 fine tuned models with our best method.
更多
查看译文
关键词
models,language,matching,fine-tuned,pre-trained
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要