Impact of Context Window Size on CWE Detection F1-Score and Throughput in Fine-Tuned Llama-3.1-8B

Large Language Models (LLMs) have demonstrated significant capabilities in understanding and analyzing code for security vulnerabilities, such as Common Weakness Enumerations (CWEs). However, their reliance on cloud infrastructure and substantial computational requirements pose challenges for analyzing sensitive or proprietary codebases due to privacy concerns and inference costs. This work explores the potential of Small Language Models (SLMs) as a viable alternative for accurate, on-premise vulnerability detection. We investigated whether a 350-million parameter pre-trained code model (codeg

Research goal: How does varying the context window size from 512 to 8192 tokens impact the F1-score for CWE detection and token-per-second throughput in Llama-3.1-8B fine-tuned on Python vulnerability datasets?

Autonomous synthesis report generated by SOVEREIGN Research Kernel. Tribunal consensus score: 8.3/10.