Predicting Disagreement with Human Raters in LLM-as-a-Judge Difficulty Assessment without Using Generation-Time Probability Signals

Documenti analoghi

• Accurate and Efficient Statistical Testing for Word Semantic Breadth
  di: Ehara, Yo
  Pubblicazione: (2026)
• Can LLMs Estimate Student Struggles? Human-AI Difficulty Alignment with Proficiency Simulation for Item Difficulty Prediction
  di: Li, Ming, et al.
  Pubblicazione: (2025)
• Can LLM be a Personalized Judge?
  di: Dong, Yijiang River, et al.
  Pubblicazione: (2024)
• MLLM-as-a-Judge for Image Safety without Human Labeling
  di: Wang, Zhenting, et al.
  Pubblicazione: (2024)
• Is GPT-4 Alone Sufficient for Automated Essay Scoring?: A Comparative Judgment Approach Based on Rater Cognition
  di: Kim, Seungju, et al.
  Pubblicazione: (2024)