Local LLM TorchSight achieves 95% accuracy in security document classification

Researchers have developed TorchSight, an open-source local system for classifying security documents using a fine-tuned Qwen 3.5 27B large language model. This system achieved 95.0% accuracy on a benchmark of 1,000 documents, significantly outperforming commercial models which scored between 75.4% and 79.9%. The fine-tuned local model demonstrates the capability to maintain data privacy while accurately identifying sensitive information across various security categories and subcategories. AI

IMPACT Demonstrates that fine-tuned local LLMs can match or exceed commercial models for sensitive data classification, enabling better privacy.

RANK_REASON The cluster contains an academic paper detailing a new open-source system and benchmark data for security document classification. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• GPT-4
• Ivan Dobrovolskyi
• Qwen 3.5 27B
• TorchSight

• paper
• product
• model release

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →