EDU-CIRCUIT-HW reveals large latent recognition failures in MLLMs on real handwritten university STEM solutions, limiting auto-grading reliability, though hybrid human-AI routing of only 3.3% cases improves outcomes.
Title resolution pending
3 Pith papers cite this work, alongside 5 external citations. Polarity classification is still indexing.
3
Pith papers citing it
5
external citations · external index
years
2026 3verdicts
UNVERDICTED 3representative citing papers
Embedding similarity of physics solutions correlates modestly with human scores but clusters are score-enriched rather than score-equivalent due to surface-feature sensitivity.
Vision LLMs achieve high rubric-level accuracy on handwritten math but most errors stem from transcription failures rather than rubric misapplication.
citing papers explorer
-
EDU-CIRCUIT-HW: Evaluating Multimodal Large Language Models on Real-World University-Level STEM Student Handwritten Solutions
EDU-CIRCUIT-HW reveals large latent recognition failures in MLLMs on real handwritten university STEM solutions, limiting auto-grading reliability, though hybrid human-AI routing of only 3.3% cases improves outcomes.
-
Testing the Validity of Embedding-Based Similarity and Clustering for Handwritten Physics Solutions
Embedding similarity of physics solutions correlates modestly with human scores but clusters are score-enriched rather than score-equivalent due to surface-feature sensitivity.
-
Automated Grading of Handwritten Mathematics Using Vision-Capable LLMs
Vision LLMs achieve high rubric-level accuracy on handwritten math but most errors stem from transcription failures rather than rubric misapplication.