GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
PolicyShiftGuard
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
PolicyShiftGuard
Model Tree
Base
Qwen/Qwen2.5-VL-7B-Instruct
Fine-tuned
this model
Input Modalities
Text
Image
Output Modalities
Text
Supported Functionality
Dedicated Endpoints
Container
text
true | <two-digit risk category id> | <short reason>false | <short reason>
This checkpoint is trained with the PolicyShiftBench public data release:
PolicyShiftBench/PolicyShiftBenchUse this model for research on policy-conditioned multimodal safety, adaptive image moderation, and robustness under policy shifts. The model should be evaluated with explicit policy bundles rather than as a fixed universal safety classifier.
This is a research checkpoint. It may fail under policies, languages, visual domains, or deployment settings not represented in the benchmark. Outputs should not be treated as legal or compliance advice.
If you use this model, please cite the paper:
bibtex
@article{song2026policyshiftguard,title = {PolicyShiftGuard: Benchmarking and Improving Policy-Adaptive Image Guardrails},author = {Song, Mingyang and Xu, Luxin and Sun, Haoyu and Pan, Minzhou and Cheng, Yu and Li, Bo},journal = {arXiv preprint arXiv:2607.05910},year = {2026}}