Towards Safer Social Media Platforms: Scalable and Performant Few-Shot Harmful Content Moderation Using Large Language Models

Name: Towards Safer Social Media Platforms: Scalable and Performant Few-Shot Harmful Content Moderation Using Large Language Models
Uploaded: 2026-09-03T04:18:45.246195+00:00
Duration: 518 s
Description: The episode discusses a paper titled "Towards Safer Social Media Platforms: Scalable and Performant Few-Shot Harmful Content Moderation Using Large Language Models." The hosts explore how this research uses Large Language Models (LLMs) to move beyond traditional keyword matching, allowing for scalable and accurate content moderation that adapts quickly to new threats.

The episode discusses a paper titled "Towards Safer Social Media Platforms: Scalable and Performant Few-Shot Harmful Content Moderation Using Large Language Models." The hosts explore how this research uses Large Language Models (LLMs) to move beyond traditional keyword matching, allowing for scalable and accurate content moderation that adapts quickly to new threats.

Open the full episode