inclusionAI releases SingProbe, a lightweight streaming guardrail for Qwen3.8-Flash-Next
AIinclusionAI releases SingProbe, a 5.18M-parameter probe on Qwen/Qwen3.8-Flash-Next that scores query intent, response unsafety, and hallucination risk at every generated token using the base model's hidden states. The probe adds less than 0.5% decode-time overhead and posts an 0.8714 F1 on response safety classification across eight benchmarks, against 0.8604 for Qwen3Guard-Gen-8B-strict.
Source details
inclusionAI (Ant Ling) · new models on Hugging Face · huggingface.coPublished · added here
Original title: inclusionAI/Qwen3.8-Flash-Next-singprobe