Functional-level Uncertainty Quantification for Calibrated Fine-tuning on LLMs

Documenti analoghi

• SimulRAG: Simulator-based RAG for Grounding LLMs in Long-form Scientific QA
  di: Xu, Haozhou, et al.
  Pubblicazione: (2025)
• Diffusion-BBO: Diffusion-Based Inverse Modeling for Online Black-Box Optimization
  di: Wu, Dongxia, et al.
  Pubblicazione: (2024)
• Multi-Fidelity Residual Neural Processes for Scalable Surrogate Modeling
  di: Niu, Ruijia, et al.
  Pubblicazione: (2024)
• Calibrated Uncertainty Quantification for Operator Learning via Conformal Prediction
  di: Ma, Ziqi, et al.
  Pubblicazione: (2024)
• Calibration Collapse Under Sycophancy Fine-Tuning: How Reward Hacking Breaks Uncertainty Quantification in LLMs
  di: Sahoo, Subramanyam
  Pubblicazione: (2026)