harmful-content

Tag

Cards List
#harmful-content

Auditing Exposure to Harmful Content on TikTok using Multimodal Language Models: A Cross-National, Age-Stratified Study

arXiv cs.CL ↗ · 2026-08-19 Cached

This study audits TikTok for harmful content exposure using multimodal language models across multiple countries and age groups, finding that keyword searches increase harmful content and that MLLMs provide a scalable tool for youth-safety audits.

0 favorites 0 likes
#harmful-content

HarmProfile: Characterizing Harmful Distributions in Frontier LLMs

arXiv cs.CL ↗ · 2026-08-18 Cached

HarmProfile is a benchmark dataset for analyzing harmful outputs from frontier LLMs, covering over 80,000 artifacts across 23 models and 15 harm categories to define model risk profiles.

0 favorites 0 likes
#harmful-content

Internal Safety Collapse in Frontier Large Language Models

Papers with Code Trending ↗ · 2026-03-04 Cached

This paper introduces Internal Safety Collapse, a critical safety failure in frontier large language models where they generate harmful content under specific task conditions, and presents ISC-Bench to evaluate it across various scenarios.

0 favorites 0 likes
← Back to home

Submit Feedback