🎯 LoRA fine-tuning

The items that name it 2

• DistillGuard: Malicious NPM Package Detection and API Attack Chain Analysis via Static Graph and LLM Distillation
  paper2026-09-24

  efficiently fine-tunes the Qwen3-8B model to support offline deployment

• Calibration Without Comprehension: Diagnosing the Limits of Fine-Tuning LLMs for Vulnerability Detection in Systems Software
  paper

  Low-rank adaptation fine-tuning applied to 15 LLM variants evaluated for vulnerability detection and CWE classification, found to shift output threshold without changing underlying decision policy ('calibration without comprehension')

In every workspace you can read 8