Understanding How Value Neurons Shape the Generation of Specified Values in LLMs

Documenti analoghi

• Understanding and Mitigating Cross-lingual Privacy Leakage via Language-specific and Universal Privacy Neurons
  di: Dong, Wenshuo, et al.
  Pubblicazione: (2025)
• Word Recovery in Large Language Models Enables Character-Level Tokenization Robustness
  di: Yang, Zhipeng, et al.
  Pubblicazione: (2026)
• Understanding and Mitigating Political Stance Cross-topic Generalization in Large Language Models
  di: Zhang, Jiayi, et al.
  Pubblicazione: (2025)
• Understanding the Repeat Curse in Large Language Models from a Feature Perspective
  di: Yao, Junchi, et al.
  Pubblicazione: (2025)
• MoRAL: MoE Augmented LoRA for LLMs' Lifelong Learning
  di: Yang, Shu, et al.
  Pubblicazione: (2024)