Wait, but Tylenol is Acetaminophen... Investigating and Improving Language Models' Ability to Resist Requests for Misinformation

Documenti analoghi

• Sparse Autoencoder Features for Classifications and Transferability
  di: Gallifant, Jack, et al.
  Pubblicazione: (2025)
• Language Models are Surprisingly Fragile to Drug Names in Biomedical Benchmarks
  di: Gallifant, Jack, et al.
  Pubblicazione: (2024)
• debiaSAE: Benchmarking and Mitigating Vision-Language Model Bias
  di: Sasse, Kuleen, et al.
  Pubblicazione: (2024)
• KScope: A Framework for Characterizing the Knowledge Status of Language Models
  di: Xiao, Yuxin, et al.
  Pubblicazione: (2025)
• MedBrowseComp: Benchmarking Medical Deep Research and Computer Use
  di: Chen, Shan, et al.
  Pubblicazione: (2025)