Promise and peril of collaborative code generation models : Balancing effectiveness and memorization

• Main Authors: CHEN, Zhi, JIANG, Lingxiao
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2024
• Subjects: Collaborative training; Memorization; Large Language Model; Code generation; Simulation evaluation; Security and privacy; Machine learning; Artificial Intelligence and Robotics; Software Engineering
• Online Access: https://ink.library.smu.edu.sg/sis_research/9967; https://ink.library.smu.edu.sg/context/sis_research/article/10967/viewcontent/ase2024collaborativeCodeModels.pdf
• Institution: Singapore Management University

In the rapidly evolving field of machine learning, training models with datasets from various locations and organizations presents significant challenges due to privacy and legal concerns. The exploration of effective collaborative training settings, which are capable of leveraging valuable knowledg...