Musubi open-sources content moderation decision model PolicyLM-1.7B

1. 04:35
   TechCrunch AI

   How Musubi's PolicyLM-1.7B decision model changes content moderation

   Musubi releases open-weight decision model PolicyLM-1.7B, which can apply content policies written in English directly to message moderation, with per-item decisions taking less than 50 milliseconds. The model's cost and speed are close to AI classifiers used by mainstream social platforms, but it has the flexibility of modern LLMs, can execute complex policies without specialized training, and requires no retraining after policy changes. Its output is a binary judgment, i.e., whether content belongs to a certain category.

1. Time not given
   Musubi Labs

   Musubi Labs open-sources PolicyLM-1.7B content moderation decision model

   Musubi Labs releases PolicyLM-1.7B, a content moderation decision model for trust and safety teams, with weights released under Apache 2.0. It reads platform custom policies and messages, returns a 0-1 score for each category in a single forward pass, does not generate text, has a median latency of 35 ms on short chat messages on a 24 GB L4 and below 100 ms overall, supports multi-label and custom labels, and policy changes take effect immediately without retraining. The model is based on BidirLM-1.7B-Embedding, derived from Qwen3-1.7B-Base, and trained on public data such as the NVIDIA Nemotron Safety Guard Dataset v3, Alibaba XGuard-Train-Open-200K, and PolyGuardMix. It is evaluated on 19 languages, with English being the strongest and Tamil the weakest. The authors state it outperforms all comparison models under 20B parameters on their self-built policy benchmark, and a fine-tuned version is already running on a platform processing over one million messages per day.

Current attention36·Peak in the comparable period43（Oct 7 18:00）·Change over the comparable past 24 hours 0%