Safety mid-training lowers LLM attack success before post-training
Authors report a 72% to 81% relative attack-success drop versus Qwen3 1.7B, 4B, and 8B bases.
Stories per day · 30 days
3 stories, newest first · one card per story
Stories tagged #mid-training
MiST: Mid-Training LLMs for Cybersecurity
MiST introduces 8B and 32B cybersecurity-specialized LLMs that outperform Qwen baselines by up to 13.1 points on public security benchmarks.
Everything in Moderation: Per-Domain Coverage Optima and Alignment-Resistant Domain Gaps in Multi-Domain Mid-Training
Controlled mid-training experiments on Qwen3-8B-Base find each domain has a 10-40% coverage optimum and domain gaps survive alignment SFT.