Megadose AI progress, ranked and analyzed.

SIRF: A Spec-Internalized Risk Foundation Model for Industrial Content Risk Control

· ArXiv · AI/CL/LG ·
SIRF’s claimed gain comes from putting platform policy into the model during continued pretraining, not from changing the verdict interface.

The paper says SIRF-8B-SFT hit 71.3% Black Recall@P95, 15.1 points above a same-source Qwen3-8B-SFT baseline. It used about 70M continued-pretraining tokens and kept deployment to a verdict-only, low-latency setup. The authors also report production use as a tree-model adjudication layer, recovering 20% more mis-penalized samples, plus a freezing-scenario transfer with about 70% relative mis-penalization reduction. ArXiv · AI/CL/LG's note

score 5

Categories: Research