Generating with Confidence: Uncertainty Quantification for Black-box Large Language Models

Documenti analoghi

• Contextualized Sequence Likelihood: Enhanced Confidence Scores for Natural Language Generation
  di: Lin, Zhen, et al.
  Pubblicazione: (2024)
• Position Paper: Generalized grammar rules and structure-based generalization beyond classical equivariance for lexical tasks and transduction
  di: Petrache, Mircea, et al.
  Pubblicazione: (2024)
• Recurrent Confidence Chain: Temporal-Aware Uncertainty Quantification in Large Language Models
  di: Mao, Zhenjiang, et al.
  Pubblicazione: (2026)
• Uncertainty Quantification for In-Context Learning of Large Language Models
  di: Ling, Chen, et al.
  Pubblicazione: (2024)
• Watermarking Degrades Alignment in Language Models: Analysis and Mitigation
  di: Verma, Apurv, et al.
  Pubblicazione: (2025)