Rethinking Prospect Theory for LLMs: Revealing the Instability of Decision-Making under Epistemic Uncertainty

Documenti analoghi

• Revisiting Epistemic Markers in Confidence Estimation: Can Markers Accurately Reflect Large Language Models' Uncertainty?
  di: Liu, Jiayu, et al.
  Pubblicazione: (2025)
• CritiCal: Can Critique Help LLM Uncertainty or Confidence Calibration?
  di: Zong, Qing, et al.
  Pubblicazione: (2025)
• Patterns Over Principles: The Fragility of Inductive Reasoning in LLMs under Noisy Observations
  di: Li, Chunyang, et al.
  Pubblicazione: (2025)
• ComparisonQA: Evaluating Factuality Robustness of LLMs Through Knowledge Frequency Control and Uncertainty
  di: Zong, Qing, et al.
  Pubblicazione: (2024)
• NAACL: Noise-AwAre Verbal Confidence Calibration for Robust LLMs in RAG Systems
  di: Liu, Jiayu, et al.
  Pubblicazione: (2026)