LicenseGPT: A Fine-tuned Foundation Model for Publicly Available Dataset License Compliance
Dataset license compliance is a critical yet complex aspect of developing commercial AI products, particularly with the increasing use of publicly available datasets. Ambiguities in dataset licenses pose significant legal risks, making it challenging even for software IP lawyers to accurately interpret rights and obligations. In this paper, we introduce LicenseGPT, a fine-tuned foundation model (FM) specifically designed for dataset license compliance analysis. We first evaluate existing legal FMs (i.e., FMs specialized in understanding and processing legal texts) and find that the best-performing model achieves a Prediction Agreement (PA) of only 43.75%. LicenseGPT, fine-tuned on a curated dataset of 500 licenses annotated by legal experts, significantly improves PA to 64.30%, outperforming both legal and general-purpose FMs. Through an A/B test and user study with software IP lawyers, we demonstrate that LicenseGPT reduces analysis time by 94.44%, from 108 seconds to 6 seconds per license, without compromising accuracy. Software IP lawyers perceive LicenseGPT as a valuable supplementary tool that enhances efficiency while acknowledging the need for human oversight in complex cases. Our work underscores the potential of specialized AI tools in legal practice and offers a publicly available resource for practitioners and researchers. Moreover, LicenseGPT has the potential to assist AI software developers in managing preliminary license checks before involving legal counsel, helping to avoid costly late-stage rework and ensuring AI software compliance.
Tue 24 JunDisplayed time zone: Amsterdam, Berlin, Bern, Rome, Stockholm, Vienna change
16:00 - 17:40 | LLM for SE 3Ideas, Visions and Reflections / Industry Papers / Demonstrations / Journal First at Cosmos 3A Chair(s): Maliheh Izadi Delft University of Technology | ||
16:00 20mTalk | LicenseGPT: A Fine-tuned Foundation Model for Publicly Available Dataset License Compliance Industry Papers JingwenTan School of Software Engineering, Sun Yat-Sen University, Gopi Krishnan Rajbahadur Centre for Software Excellence, Huawei, Canada, Zi Li Huawei China, xiangfu song Huawei Canada Research Centre, jianshan lin Huawei Technologies Co. Ltd, Dan Li Sun Yat-sen University, Zibin Zheng Sun Yat-sen University, Ahmed E. Hassan Queen’s University | ||
16:20 20mTalk | LLM-Augmented Ticket Aggregation for Low-cost Mobile OS Defect Resolution Industry Papers Yongqian Sun Nankai University, Bowen Hao Nankai University, Xiaotian Wang Nankai University, Chenyu Zhao Nankai University, Yongxin Zhao , Binpeng Shi Nankai University, Shenglin Zhang Nankai University, Qiao Ge Huawei Inc., Wenhu Li Huawei Inc., Hua Wei Huawei Inc., Dan Pei Tsinghua University | ||
16:40 20mTalk | On the Workflows and Smells of Leaderboard Operations (LBOps): An Exploratory Study of Foundation Model Leaderboards Journal First Zhimin Zhao Queen's University, Abdul Ali Bangash Queen's University, Filipe Cogo Centre for Software Excellence, Huawei Canada, Bram Adams Queen's University, Ahmed E. Hassan Queen’s University | ||
17:00 10mTalk | CodingGenie: A Proactive LLM-Powered Programming Assistant Demonstrations Sebastian Zhao University of California, Berkeley, Alan Zhu Carnegie Mellon University, Hussein Mozannar Microsoft Research, David Sontag MIT, Ameet Talwalkar Carnegie Mellon University, Valerie Chen Carnegie Mellon University | ||
17:10 10mTalk | Collaboration is all you need: LLM Assisted Safe Code Translation Ideas, Visions and Reflections Rabimba Karanjai University of Houston, Sam Blackshear Mysten Labs, Lei Xu Kent State University, Weidong Shi University of Houston | ||
17:20 20mTalk | Exploring Variable Potential for LLM-based Log Parsing Efficiency and Reduced Costs Ideas, Visions and Reflections Jinrui Sun Peking University, Tong Jia Institute for Artificial Intelligence, Peking University, Beijing, China, Minghua He Peking University, Yihan Wu National Computer Network Emergency Response Technical Team/Coordination Center of China, Ying Li School of Software and Microelectronics, Peking University, Beijing, China, Gang Huang Peking University | ||
Cosmos 3A is the first room in the Cosmos 3 wing.
When facing the main Cosmos Hall, access to the Cosmos 3 wing is on the left, close to the stairs. The area is accessed through a large door with the number “3”, which will stay open during the event.