WALKSAFE: Risk-aware Graph Random Walk with Bi-GRPO for LLM Safety.
Shilong Pan, Zhiliang Tian, Wanlong Yu, Zhen Huang, Qingyu Qiu, Zihan Chen, Zhonghao Sun, Minlie Huang, Dongsheng Li
Browse the full AAAI paper archive.
Shilong Pan, Zhiliang Tian, Wanlong Yu, Zhen Huang, Qingyu Qiu, Zihan Chen, Zhonghao Sun, Minlie Huang, Dongsheng Li
Browse the full AAAI paper archive.