Roblox deploys AI chat rephrasing to replace profanity with respectful language in real time

Roblox Introduces AI-Powered Tool to Moderate In-Game Chat

Roblox has deployed a new AI system that rephrases chat messages in real time to remove banned language, marking a significant shift from its previous approach of simply replacing offensive words with hashtag symbols. The gaming platform, which boasts 151.5 million daily active users, announced that its AI-powered content filtering system will now translate profanity and inappropriate phrases "into more respectful language that remains closer to the user's original intent," according to Rajiv Bhatia, Roblox VP of User and Discovery Product1

1

. The change addresses a longstanding issue where excessive hashtags disrupted conversations and made chats difficult to follow4

4

.

The real-time chat rephraser works by automatically detecting when players use problematic words or phrases, then swaps banned words for respectful text before the message appears in chat. For example, "Hurry TF up" becomes "Hurry up," and "oh shit, are you OK?" is transformed into "are you OK?"1

1

. Everyone in the chat receives a notification that AI has rephrased the message to maintain civility, while only the sender sees a warning about using improper language2

2

.

Advanced Detection Capabilities Replace Inappropriate Language

The AI system goes beyond simple word matching to detect sophisticated attempts at bypassing filters. Roblox's technology can now identify leet-speak, where letters are replaced with numbers or symbols, as well as abbreviations and other creative workarounds players use to circumvent content filtering1

1

. When the AI encounters new slang or phrases it cannot immediately classify, the system escalates the content to a larger, more highly trained AI model that can deduce meaning from context1

1

.

Bhatia stated that experiments show "this combined approach has significantly improved our filters," with early results demonstrating a 20x reduction in false negatives when users attempt to share or solicit personal information5

5

. The company trains its specialized AI models using a combination of larger language models and in-game chat samples to stay current with evolving online language patterns1

1

.

Censoring Chats with AI Amid Safety Concerns

The chat rephrasing feature is currently available only for in-game chats between players who have completed age verification and belong to similar age groups2

2

. The system supports all 16 languages available through Roblox's automatic translation tool, including English, Spanish, Russian, French, Chinese, Arabic, and German3

3

. Players who repeatedly attempt to circumvent the system or continue using banned words will still face disciplinary action under the platform's Community Standards rules1

1

.

The rollout comes just two months after Roblox introduced mandatory facial verification for chat access, which sorts users into age groups to limit contact between children and adults1

1

. By February, approximately 45% of the platform's users had completed the facial checks processed by third-party vendor Persona3

3

.

Lawsuits Challenge Child Safety Efforts

Despite implementing stricter controls, Roblox faces mounting legal pressure over allegations of child safety failures. Nebraska filed a lawsuit in March targeting the platform's alleged inadequacies in protecting minors, joining Texas, Florida, Louisiana, Kentucky, and several municipalities in legal action against the company1

1

. Louisiana's Attorney General filed suit claiming Roblox "created a public park and filled it with sex predators that are preying on... children," while LA County alleged in February that the platform "makes children easy prey for pedophiles"4

4

.

Bhatia emphasized that the new approach creates "a flywheel for civility, where real-time feedback helps users learn and adopt our Community Standards"4

4

. While the system may still produce false positives and require time to learn emerging slang, Roblox expects it will accurately handle most situations. The company's focus on reducing friction in chat while maintaining standards reflects broader industry challenges in balancing open communication with user safety, particularly for platforms where most users are minors.