# Fine-tuning RoBERTa for CVE-to-CWE Classification: A 125M Parameter Model Competitive with LLMs

arXiv: https://arxiv.org/abs/2603.14911 · HTML: https://mlsanity.com/paper/2603.14911/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 12 references that are in the map.
- First posted on arXiv 16 Mar 2026.

## Builds on (most cited first, 8 of 8)

- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [CTIBench: A Benchmark for Evaluating LLMs in Cyber Threat Intelligence](https://mlsanity.com/paper/2406.07599/) (2024)
- [SecureBERT: A Domain-Specific Language Model for Cybersecurity](https://mlsanity.com/paper/2204.02685/) (2022)
- [Llama-3.1-FoundationAI-SecurityLLM-Base-8B Technical Report](https://mlsanity.com/paper/2504.21039/) (2025)
- [Primus: A Pioneering Collection of Open-Source Datasets for Cybersecurity LLM Training](https://mlsanity.com/paper/2502.11191/) (2025)
- [V2W-BERT: A Framework for Effective Hierarchical Multiclass Classification of Software Vulnerabilities](https://mlsanity.com/paper/2102.11498/) (2021)
- [Llama-3.1-FoundationAI-SecurityLLM-Reasoning-8B Technical Report](https://mlsanity.com/paper/2601.21051/) (2026)
- [Automated CVE Analysis for Threat Prioritization and Impact Prediction](https://mlsanity.com/paper/2309.03040/) (2023)

## Abstract (arXiv)

We present a fine-tuned RoBERTa-base classifier (125M parameters) for mapping Common Vulnerabilities and Exposures (CVE) descriptions to Common Weakness Enumeration (CWE) categories. We construct a large-scale training dataset of 234,770 CVE descriptions with AI-refined CWE labels using Claude Sonnet 4.6, and agreement-filtered evaluation sets where NVD and AI labels agree. On our held-out test set (27,780 samples, 205 CWE classes), the model achieves 87.4% top-1 accuracy and 60.7% Macro F1 -- a +15.5 percentage-point Macro F1 gain over a TF-IDF baseline that already reaches 84.9% top-1, demonstrating the model's advantage on rare weakness categories. On the external CTI-Bench benchmark (NeurIPS 2024), the model achieves 75.6% strict accuracy (95% CI: 72.8-78.2%) -- statistically indistinguishable from Cisco Foundation-Sec-8B-Reasoning (75.3%, 8B parameters) at 64x fewer parameters. We release the dataset, model, and training code.