Toxicity Detection Should Measure Contextual Harm, Not Text-Intrinsic Badness

Documenti analoghi

• Evading Toxicity Detection with ASCII-art: A Benchmark of Spatial Attacks on Moderation Systems
  di: Berezin, Sergey, et al.
  Pubblicazione: (2024)
• The TIP of the Iceberg: Revealing a Hidden Class of Task-in-Prompt Adversarial Attacks on LLMs
  di: Berezin, Sergey, et al.
  Pubblicazione: (2025)
• Towards Cross-Lingual Audio Abuse Detection in Low-Resource Settings with Few-Shot Learning
  di: Sankaran, Aditya Narayan, et al.
  Pubblicazione: (2024)
• Towards Detecting Contextual Real-Time Toxicity for In-Game Chat
  di: Yang, Zachary, et al.
  Pubblicazione: (2023)
• AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents
  di: Andriushchenko, Maksym, et al.
  Pubblicazione: (2024)