Evaluating LLMs Without Oracle Feedback: Agentic Annotation Evaluation Through Unsupervised Consistency Signals

Documenti analoghi

• Exploring the Effectiveness and Interpretability of Texts in LLM-based Time Series Models
  di: Sun, Zhengke, et al.
  Pubblicazione: (2025)
• HC$^2$L: Hybrid and Cooperative Contrastive Learning for Cross-lingual Spoken Language Understanding
  di: Xing, Bowen, et al.
  Pubblicazione: (2024)
• Activation Oracles: Training and Evaluating LLMs as General-Purpose Activation Explainers
  di: Karvonen, Adam, et al.
  Pubblicazione: (2025)
• Are LLMs Prescient? A Continuous Evaluation using Daily News as the Oracle
  di: Dai, Hui, et al.
  Pubblicazione: (2024)
• Time-Reversal Provides Unsupervised Feedback to LLMs
  di: Varun, Yerram, et al.
  Pubblicazione: (2024)