Yuvion LLM: An Adversarially-Aware Large Language Model for Content And AI Safety
About
As large language models are increasingly deployed in real-world systems, safety failures can still lead to harmful outputs and dangerous misuse. We argue that the essence of safety is adversarial: many failures arise not from natural inputs alone, but from strategic attempts to evade model policies and safeguards. However, existing general-purpose model development largely overlook this adversarial nature, and often remain insufficient for realistic safety scenarios involving planning, tool use, and multi-step reasoning, causing measured safety performance to overestimate real deployment robustness. To address this gap, we present Yuvion LLM, a large language model built for adversarially robust content safety and broader AI safety. Yuvion LLM treats adversarial robustness and agentic capability as first-class objectives. Its pipeline combines adversarially aware data construction, knowledge-enhanced continued pretraining, and policy-grounded multi-task safety post-training, including risk-aware supervised fine-tuning and reinforcement learning-based policy optimization, together with safety-aware agentic reinforcement learning for tool use and multi-step reasoning in complex safety scenarios. We further introduce the Yuvion LLM RiskEval (YLRE), a collection of 93 benchmarks across four evaluation categories, covering diverse open and internal evaluations with a focus on safety, adversarial robustness, and real-world capability requirements. Across these evaluations, Yuvion LLM demonstrates clear advantages on safety-focused benchmarks and particularly strong robustness under adversarial conditions, while maintaining solid overall capability. Notably, Yuvion-8B outperforms most state-of-the-art baselines, including substantially larger models such as GPT-5.4 and Qwen3-MAX, on several safety tasks.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Hate Speech Detection | HateXplain (test) | Macro F1 Score63.6 | 44 | |
| Content Moderation | Dynamic Evaluation Sets Adversarial 1.0 | Overall Composite Score86.72 | 22 | |
| Content Moderation and Data Security | in-house business benchmarks | Overall Accuracy87.34 | 22 | |
| Domain Capability Evaluation | in-house domain capability benchmarks | Overall Performance86.1 | 22 | |
| Content Safety Classification | Static Content Safety Evaluation Sets | Adv. & Traffic94.3 | 9 | |
| Agentic Capability | API-Bank | Accuracy90.45 | 8 | |
| Content Safety | ChineseHarm (test) | Macro F1-Score97.9 | 8 | |
| Content Safety | ToxiGen (test) | Macro F1-Score86 | 8 | |
| Content Safety | Jigsaw (test) | Macro F1-Score76 | 8 | |
| Content Safety | CivilComments (test) | Macro F1-Score65.4 | 8 |