There Is More to Refusal in Large Language Models than a Single Direction

Documenti analoghi

• Beyond the Leaderboard: Understanding Performance Disparities in Large Language Models via Model Diffing
  di: Boughorbel, Sabri, et al.
  Pubblicazione: (2025)
• Improving Language Models Trained on Translated Data with Continual Pre-Training and Dictionary Learning Analysis
  di: Boughorbel, Sabri, et al.
  Pubblicazione: (2024)
• Scaling up Discovery of Latent Concepts in Deep NLP Models
  di: Hawasly, Majd, et al.
  Pubblicazione: (2023)
• FanarGuard: A Culturally-Aware Moderation Filter for Arabic Language Models
  di: Fatehkia, Masoomali, et al.
  Pubblicazione: (2025)
• Do I Really Know? Learning Factual Self-Verification for Hallucination Reduction
  di: Altinisik, Enes, et al.
  Pubblicazione: (2026)