When VLMs 'Fix' Students: Identifying and Penalizing Over-Correction in the Evaluation of Multi-line Handwritten Math OCR

Documenti analoghi

• MemEIC: A Step Toward Continual and Compositional Knowledge Editing
  di: Seong, Jin, et al.
  Pubblicazione: (2025)
• Do LLMs Need Inherent Reasoning Before Reinforcement Learning? A Study in Korean Self-Correction
  di: Kim, Hongjin, et al.
  Pubblicazione: (2026)
• Enhancing Automated Essay Scoring with Three Techniques: Two-Stage Fine-Tuning, Score Alignment, and Self-Training
  di: Choi, Hongseok, et al.
  Pubblicazione: (2026)
• Benchmarking Large Language Models for Diagnosing Students' Cognitive Skills from Handwritten Math Work
  di: Kim, Yoonsu, et al.
  Pubblicazione: (2025)
• Can Vision-Language Models Evaluate Handwritten Math?
  di: Nath, Oikantik, et al.
  Pubblicazione: (2025)