Jum Blog
NewsArticlesProjectsAbout
  1. Home
  2. ›
  3. News
  4. ›
  5. papers
📁 Category

papers · 2 topics

学術論文 (arXiv / 会議 / 研究機関ブログ)
llm2bias1ffn1hallucination1interpretability1mechanistic interpretability1model evaluation1safety1stereotypes1

2026 · Apr

04-24🔥🔥

Can We Locate and Prevent Stereotypes in LLMs?

04-24🔥🔥

Do Hallucination Neurons Generalize? Evidence from Cross-Domain Transfer in LLMs

© Jumtra Blog 2026.