Event date · · Ant Group

inclusionAI open-sourced Qwen3-8B-singprobe, a streaming safety and hallucination probe

Ant Group 蚂蚁集团Chinese AIOpen weights
FACT STATEMENT

inclusionAI released Qwen3-8B-singprobe, an Apache-2.0 licensed streaming guardrail probe built on Qwen3-8B, on Hugging Face. It adds less than 0.5% decode-time overhead and scores query intent, response unsafety, and hallucination risk at every token.

China context

Original name
inclusionAI
Outside China
Open weights · huggingface.co
Claims
Company-reported; not yet independently evaluated
For builders
Developers outside China can download the Apache-2.0 weights from Hugging Face and integrate via SGLang or vLLM branches to add streaming safety scoring to Qwen3-8B.
For investors
The release signals Ant Group's continued investment in open-weights safety tooling, which may pressure commercial guardrail vendors.
What happened

inclusionAI released Qwen3-8B-singprobe on Hugging Face under Apache-2.0. The probe reuses Qwen3-8B hidden states to score query intent, response unsafety, and hallucination risk per token, with less than 0.5% decode-time overhead. It is supported via SGLang and vLLM integration branches.

Technical significance

The probe taps layers [10, 22, 34] of Qwen3-8B and adds 8.13M parameters. Reported F1 scores: 0.8687 for query intent, 0.8616 for response safety, 0.9878 R-AUC for streaming safety, and 0.7849 AUC for hallucination detection. Benign-response false-positive rate is 0.03% across 5 datasets.

Industry impact

Developers deploying Qwen3-8B can add streaming safety and hallucination scoring without a separate safety model, reducing inference cost and latency. Competitors offering guardrail models must match sub-0.5% overhead and per-token scoring to remain attractive.

Decision value

The probe lowers the cost and complexity of adding safety and hallucination detection to Qwen3-8B deployments, potentially increasing enterprise adoption of the base model.

What to watch

Next signals to check: adoption of the SGLang/vLLM integration branches, independent benchmarks against the reported metrics, and whether inclusionAI releases probes for other base models.

Latest in Chinese AI

  1. DeepSeekReportedly: DeepSeek V1 author’s startup project is an open-source agent for local deployment
  2. DeepSeekReportedly: OpenDesign team's OpenMotion lets DeepSeek Harness create motion graphics
  3. XiaomiReportedly: Xiaomi adds MiMo UltraSpeed to Token Plan Pro and Max for a limited time
  4. MiniMaxMiniMax publishes cryptanalysis findings from its internal AI model
  5. DeepSeekReportedly: Simplex AI founder Tony Zhang open-sources Linger, a personal agent that can run locally

All China AI Events

AIGC Newsletter

China AI, with sources and context.

Analysis of Chinese AI models, companies and policy, and what you can use outside China.