Fine-Tuned LLMs Know They Don't Know: A Parameter-Efficient Approach to Recovering Honesty

Documenti analoghi

• Towards Objective Fine-tuning: How LLMs' Prior Knowledge Causes Potential Poor Calibration?
  di: Wang, Ziming, et al.
  Pubblicazione: (2025)
• Can AI Assistants Know What They Don't Know?
  di: Cheng, Qinyuan, et al.
  Pubblicazione: (2024)
• What Models Know, How Well They Know It: Knowledge-Weighted Fine-Tuning for Learning When to Say "I Don't Know"
  di: Lee, Joosung, et al.
  Pubblicazione: (2026)
• Do Retrieval Augmented Language Models Know When They Don't Know?
  di: Zhou, Youchao, et al.
  Pubblicazione: (2025)
• Do We Know What LLMs Don't Know? A Study of Consistency in Knowledge Probing
  di: Zhao, Raoyuan, et al.
  Pubblicazione: (2025)