Do "New Snow Tablets" Contain Snow? Large Language Models Over-Rely on Names to Identify Ingredients of Chinese Drugs

Documenti analoghi

• Enhancing LLM Character-Level Manipulation via Divide and Conquer
  di: Xiong, Zhen, et al.
  Pubblicazione: (2025)
• Fact or Guesswork? Evaluating Large Language Models' Medical Knowledge with Structured One-Hop Judgments
  di: Li, Jiaxi, et al.
  Pubblicazione: (2025)
• DRS: Deep Question Reformulation With Structured Output
  di: Li, Zhecheng, et al.
  Pubblicazione: (2024)
• Con-ReCall: Detecting Pre-training Data in LLMs via Contrastive Decoding
  di: Wang, Cheng, et al.
  Pubblicazione: (2024)
• Vulnerability of LLMs to Vertically Aligned Text Manipulations
  di: Li, Zhecheng, et al.
  Pubblicazione: (2024)