A fine-tuned local Qwen 3.5 27B model achieves 95% category-level accuracy on security document classification, outperforming commercial models on both internal and external test sets while keeping processing local.
Available at: https://www-cdn.anthropic.com/4263b940cabb546aa0e3283f35b686f4f3b2ff47.pdf (accessed 26 April 2026)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Security Document Classification with a Fine-Tuned Local Large Language Model: Benchmark Data and an Open-Source System
A fine-tuned local Qwen 3.5 27B model achieves 95% category-level accuracy on security document classification, outperforming commercial models on both internal and external test sets while keeping processing local.