Giulio Zizzo, Ambrish Rawat, Gabriele Picco, Yufang Hou, Taesung Lee, Myles Foley
We lifted 1 functions out of this paper's own repositories and ran 1 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| ibm/model-attribution-in-machine-learning | canonical | 1 of 1 |
| Function | Status | Where it lives |
|---|---|---|
| truncate_prompt | Ran | ibm/model-attribution-in-machine-learning/compute_responses/compute_responses.py code served (permissive licence) · get_code("92d7fc1c7ab289c3") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
The wide applicability and adaptability of generative large language models (LLMs) has enabled their rapid adoption. While the pretrained 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.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2306.09308")
get_code_for_paper("2306.09308")
have("2306.09308")
Connect an agent — have() is free.