Calibrating the Confidence of Large Language Models by Eliciting Fidelity

Documenti analoghi

• MetaAlign: Align Large Language Models with Diverse Preferences during Inference Time
  di: Zhang, Mozhi, et al.
  Pubblicazione: (2024)
• Thus Spake Long-Context Large Language Model
  di: Liu, Xiaoran, et al.
  Pubblicazione: (2025)
• LongSafety: Enhance Safety for Long-Context LLMs
  di: Huang, Mianqiu, et al.
  Pubblicazione: (2024)
• Domain2Vec: Vectorizing Datasets to Find the Optimal Data Mixture without Training
  di: Zhang, Mozhi, et al.
  Pubblicazione: (2025)
• SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Models
  di: Zhang, Xin, et al.
  Pubblicazione: (2023)