When Safety Blocks Sense: Measuring Semantic Confusion in LLM Refusals

Documenti analoghi

• Align Where the Words Look: Cross-Attention-Guided Patch Alignment with Contrastive and Transport Regularization for Bengali Captioning
  di: Anonto, Riad Ahmed, et al.
  Pubblicazione: (2025)
• When Refusals Fail: Unstable Safety Mechanisms in Long-Context LLM Agents
  di: Hadeliya, Tsimur, et al.
  Pubblicazione: (2025)
• Bengali Text Classification: An Evaluation of Large Language Model Approaches
  di: Hoque, Md Mahmudul, et al.
  Pubblicazione: (2026)
• Think Before Refusal : Triggering Safety Reflection in LLMs to Mitigate False Refusal Behavior
  di: Si, Shengyun, et al.
  Pubblicazione: (2025)
• Poison Once, Refuse Forever: Weaponizing Alignment for Injecting Bias in LLMs
  di: Mamun, Md Abdullah Al, et al.
  Pubblicazione: (2025)