Paper ID: 2302.06716
Machine Learning Model Attribution Challenge
Elizabeth Merkhofer, Deepesh Chaudhari, Hyrum S. Anderson, Keith Manville, Lily Wong, João Gante
We present the findings of the Machine Learning Model Attribution Challenge. Fine-tuned machine learning models may derive from other trained models without obvious attribution characteristics. In this challenge, participants identify the publicly-available base models that underlie a set of anonymous, fine-tuned large language models (LLMs) using only textual output of the models. Contestants aim to correctly attribute the most fine-tuned models, with ties broken in the favor of contestants whose solutions use fewer calls to the fine-tuned models' API. The most successful approaches were manual, as participants observed similarities between model outputs and developed attribution heuristics based on public documentation of the base models, though several teams also submitted automated, statistical solutions.
Submitted: Feb 13, 2023