Latest Articles for Content Moderation

CAST offers a precise approach to managing language model responses.

Examining how flagging mechanisms influence user trust and perceptions of fairness.

Using open-source models to improve harmful content detection efficiently and effectively.

A new dataset aims to improve the classification of harmful content online.

Examining how labeling strategies affect minority voices in sexism detection.

New methods improve detection of offensive language using sentiment analysis.

Exploring new methods for effective social media content moderation.

Examining the support and harm of online spaces for eating disorders.

The SAFE-MEME framework helps identify hate speech hidden in memes.