When Can We Trust LLM Graders? Calibrating Confidence for Automated Assessment

Documenti analoghi

• Simulating Students or Sycophantic Problem Solving? On Misconception Faithfulness of LLM Simulators
  di: Do, Heejin, et al.
  Pubblicazione: (2026)
• When Can We Trust LLMs in Mental Health? Large-Scale Benchmarks for Reliable LLM Evaluation
  di: Badawi, Abeer, et al.
  Pubblicazione: (2025)
• MalAlgoQA: Pedagogical Evaluation of Counterfactual Reasoning in Large Language Models and Implications for AI in Education
  di: Liu, Naiming, et al.
  Pubblicazione: (2024)
• LLM-based Cognitive Models of Students with Misconceptions
  di: Sonkar, Shashank, et al.
  Pubblicazione: (2024)
• Atomic Learning Objectives Labeling: A High-Resolution Approach for Physics Education
  di: Liu, Naiming, et al.
  Pubblicazione: (2024)