From One to Many: Expanding the Scope of Toxicity Mitigation in Language Models

Documenti analoghi

• Multilingual Arbitrage: Optimizing Data Pools to Accelerate Multilingual Progress
  di: Odumakinde, Ayomide, et al.
  Pubblicazione: (2024)
• The Multilingual Alignment Prism: Aligning Global and Local Preferences to Reduce Harm
  di: Aakanksha, et al.
  Pubblicazione: (2024)
• RLHF Can Speak Many Languages: Unlocking Multilingual Preference Optimization for LLMs
  di: Dang, John, et al.
  Pubblicazione: (2024)
• Whispering Experts: Neural Interventions for Toxicity Mitigation in Language Models
  di: Suau, Xavier, et al.
  Pubblicazione: (2024)
• Language Models can perform Single-Utterance Self-Correction of Perturbed Reasoning
  di: Silver, Sam, et al.
  Pubblicazione: (2025)