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.

Google self-driving car finally causes an accident -- a lesson in AI. According to The Verge, Google had recently performed a software update that changed the behavior to be more human like. "So several weeks ago we began giving the self-driving car the capabilities it needs to do what human drivers do: hug the rightmost side of the lane." The truth is that one of the complaints about self-driving cars is that they are too cautious so Google adapted the software so the car would move to the far right of the lane so two cars could fit in the single wide lane. This is what a regular, old fashioned, human being does so cars can move more fluidly though the heavily congested streets of California.