Roblox
/

roblox-pii-classifier-v2

Text Classification

text-embeddings-inference

Model card Files Files and versions

Update README.md

#2

by jordansren - opened 7 days ago

base: refs/heads/main

←

from: refs/pr/2

Discussion Files changed

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -14,14 +14,14 @@ datasets:
 - nvidia/Nemotron-PII
 ---
-# Roblox PII Classifier v2.0 — Model Card
 ## Overview
 We present `Roblox/roblox-pii-classifier-v2`, an upgraded, context-aware PII (Personally Identifiable Information) detection model. Built on the [XLM-RoBERTa-Large](https://huggingface.co/xlm-roberta-large) architecture, v2 is designed to identify attempts to share or solicit personal information across complex, multi-user conversations.
 Unlike its predecessor and other NER models, **v2 evaluates text within its surrounding conversational context**, allowing it to detect sophisticated, adversarial bypass attempts (e.g., collaborative PII exchange, phonetic spelling, implicit references) while drastically reducing false positives. It is intended for use in casual conversations, ensuring freedom of speech while also maintaining safety.
-## What’s New in v2.0?
 * **Conversational Context Integration:** Evaluates target messages within the broader multi-user chat context, eliminating ambiguity inherent in isolated messages.
 * **Massive Multilingual Expansion:** Broadened synthetic data generation and fine-tuning capabilities to expand language coverage from **17 to 189 languages**.

 - nvidia/Nemotron-PII
 ---
+# Roblox PII Classifier v2
 ## Overview
 We present `Roblox/roblox-pii-classifier-v2`, an upgraded, context-aware PII (Personally Identifiable Information) detection model. Built on the [XLM-RoBERTa-Large](https://huggingface.co/xlm-roberta-large) architecture, v2 is designed to identify attempts to share or solicit personal information across complex, multi-user conversations.
 Unlike its predecessor and other NER models, **v2 evaluates text within its surrounding conversational context**, allowing it to detect sophisticated, adversarial bypass attempts (e.g., collaborative PII exchange, phonetic spelling, implicit references) while drastically reducing false positives. It is intended for use in casual conversations, ensuring freedom of speech while also maintaining safety.
+## What’s New in v2?
 * **Conversational Context Integration:** Evaluates target messages within the broader multi-user chat context, eliminating ambiguity inherent in isolated messages.
 * **Massive Multilingual Expansion:** Broadened synthetic data generation and fine-tuning capabilities to expand language coverage from **17 to 189 languages**.