LATIDIA · Ciberseguridad

MiST: LLM de capacitación intermedia para ciberseguridad

arXiv: 2609.18496v1Tipo de anuncio: nuevo Resumen: La ciberseguridad combina un análisis de alto riesgo con un lenguaje técnico complejo, lo que lo convierte en un dominio impactante y desafiante para los LLM. Presentamos MiST (Mid-trained Security T

La noticia

arXiv:2609.18496v1 Announce Type: new Abstract: Cybersecurity combines high-stakes analysis with complex technical language, making it an impactful and challenging domain for LLMs. We present MiST (Mid-trained Security Transformer), a suite of 8B and 32B models that achieve strong performance on public cybersecurity benchmarks. We use mid-training as an intermediate adaptation stage between general pre-training and cybersecurity training. Rather than performing continual pre-training over large volumes of raw domain text, we curate a compact, expert-vetted seed corpus, and transform it into high-quality domain-specific synthetic training data. The final MiST checkpoints improve mean cybersecurity accuracy by +13.1 and +8.6 absolute percentage points over the corresponding Qwen baselines for 8B and 32B, respectively,