Is GPT-4o mini Blinded by its Own Safety Filters? Exposing the Multimodal-to-Unimodal Bottleneck in Hate Speech Detection

Documenti analoghi

• Multidimensional Analysis of Specific Language Impairment Using Unsupervised Learning Through PCA and Clustering
  di: Selvanayagam, Niruthiha
  Pubblicazione: (2025)
• Advancing Hate Speech Detection with Transformers: Insights from the MetaHate
  di: Chapagain, Santosh, et al.
  Pubblicazione: (2025)
• HateTinyLLM : Hate Speech Detection Using Tiny Large Language Models
  di: Sen, Tanmay, et al.
  Pubblicazione: (2024)
• Self-Admitted Technical Debt in LLM Software: An Empirical Comparison with ML and Non-ML Software
  di: Selvanayagam, Niruthiha, et al.
  Pubblicazione: (2026)
• Hate Speech Detection with Generalizable Target-aware Fairness
  di: Chen, Tong, et al.
  Pubblicazione: (2024)