RL‑driven constructive safety alignment lets LLMs answer risky prompts helpfully
Oyster-II replaces the SFT‑based safety fine‑tuning of Oyster‑I with a reinforcement‑learning loop that rewards helpful, safe responses instead of refusals. The RL framework closes gaps on out‑of‑distribution queries and avoids over‑generalising safety reasoning, beating Qwen3‑14B and even rivaling much larger models on safety benchmarks.