Engagement Undermines Safety: How Stereotypes and Toxicity Shape Humor in Language Models

Ähnliche Einträge

• Language Models can Subtly Deceive Without Lying: A Case Study on Strategic Phrasing in Legislation
  von: Dogra, Atharvan, et al.
  Veröffentlicht: (2024)
• PromptRefine: Enhancing Few-Shot Performance on Low-Resource Indic Languages with Example Selection from Related Example Banks
  von: Ghosal, Soumya Suvra, et al.
  Veröffentlicht: (2024)
• Safety Recovery in Reasoning Models Is Only a Few Early Steering Steps Away
  von: Ghosal, Soumya Suvra, et al.
  Veröffentlicht: (2026)
• Relic: Enhancing Reward Model Generalization for Low-Resource Indic Languages with Few-Shot Examples
  von: Ghosal, Soumya Suvra, et al.
  Veröffentlicht: (2025)
• IntCoOp: Interpretability-Aware Vision-Language Prompt Tuning
  von: Ghosal, Soumya Suvra, et al.
  Veröffentlicht: (2024)