Content Moderation Comparison Hub
4 papers - avg viability 6.0
Top Papers
- KID: Knowledge-Injected Dual-Head Learning for Knowledge-Grounded Harmful Meme Detection(7.0)
KID provides state-of-the-art knowledge-grounded harmful meme detection with a dual-head learning architecture.
- Detection of Illicit Content on Online Marketplaces using Large Language Models(7.0)
A multilingual illicit content detection tool for online marketplaces using LLMs to improve safety and moderation.
- FlexGuard: Continuous Risk Scoring for Strictness-Adaptive LLM Content Moderation(5.0)
Develop FlexGuard, an adaptable AI moderation tool that assigns risk scores for content across various strictness levels to improve moderation accuracy and robustness.
- GMP: A Benchmark for Content Moderation under Co-occurring Violations and Dynamic Rules(5.0)
Develop a benchmark for AI content moderation tackling co-occurring violations and dynamic rule changes.