Simplifying Post-Silicon Diagnostics Using Large Language Models for Advanced Node Yield Improvement
Keywords:
Large Language Models, Post-Silicon Diagnostics, Semiconductor Yield Improvement, Scan Based Testing, Continuous Learning FrameworkAbstract
The semiconductor industry faces significant challenges in post-silicon diagnostics as manufacturingprocesses advance toward smaller technology nodes, where increased integration complexity leads to exponentially growing defect types and reliability concerns that substantially impact product yield
References
Sunghoon Kim et al., "Scan Chain Architecture With Data Duplication for Multiple Scan Cell Fault Diagnosis," IEEE Xplore, 2022, https://ieeexplore.ieee.org/document/9964073
Juan F Gaitan Guerrero et al., "A novel fine-tuning and evaluation methodology for large language models on IoT raw data summaries (LLM-RawDMeth): A joint perspective in diabetes care," ScienceDirect, September 2025. https://www.sciencedirect.com/science/article/pii/S0169260725002950
