Qwen3-8B-singprobe

Qwen3-8B-singprobe

Model Description

SingProbe is an intrinsic streaming guardrail built on Qwen/Qwen3-8B. Rather than running a separate safety model, this lightweight probe reuses the base model's hidden states during generation to score, at every token, query intent, response unsafety, and hallucination risk. It adds less than 0.5% decode-time overhead.

See the technical report for methodology and complete results. Training codes are available at inclusionAI/SingProbe.

Evaluation

Higher is better for every metric. Results are averages over the benchmark suites specified below.

Quick Start

SingProbe is supported through the SGLang integration branch or vLLM integration branch. Load the probe by its Hugging Face ID at server launch:

python -m sglang.launch_server \
  --model-path Qwen/Qwen3-8B \
  --probe-ckpt inclusionAI/Qwen3-8B-singprobe \
  --port 30000

The integrations return one score dictionary per generated token (label_0–label_9). Use the exact base-model/probe pair: Qwen/Qwen3-8B with this checkpoint.

Citation

@article{singteam2026singprobe,
  title = {SingProbe Technical Report},
  author = {Sing Team},
  journal = {arXiv preprint arXiv:2608.30703},
  year = {2026},
}