Gradients with Respect to Semantics Preserving Embeddings Tell the Uncertainty of Large Language Models

Documenti analoghi

• ESI: Epistemic Uncertainty Quantification via Semantic-preserving Intervention for Large Language Models
  di: Li, Mingda, et al.
  Pubblicazione: (2025)
• Unraveling and Mitigating Retriever Inconsistencies in Retrieval-Augmented Large Language Models
  di: Li, Mingda, et al.
  Pubblicazione: (2024)
• Improving Uncertainty Quantification in Large Language Models via Semantic Embeddings
  di: Grewal, Yashvir S., et al.
  Pubblicazione: (2024)
• Semantic Structure in Large Language Model Embeddings
  di: Kozlowski, Austin C., et al.
  Pubblicazione: (2025)
• Large Language Models Preserve Semantic Isotopies in Story Continuations
  di: Cavazza, Marc
  Pubblicazione: (2025)