A hybrid confidence framework for LLM-based short answer grading combines model signals with aleatoric uncertainty from semantic clustering of responses and improves selective grading reliability over single-source methods.
Machine learning110(3), 457– 506 (2021)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
A multi-stage pipeline uses model-based screening followed by ML surrogates to explore high-dimensional stochastic agent-based models and identify unstable regions.
citing papers explorer
-
Confidence Estimation in Automatic Short Answer Grading with LLMs
A hybrid confidence framework for LLM-based short answer grading combines model signals with aleatoric uncertainty from semantic clustering of responses and improves selective grading reliability over single-source methods.
-
From Model-Based Screening to Data-Driven Surrogates: A Multi-Stage Workflow for Exploring Stochastic Agent-Based Models
A multi-stage pipeline uses model-based screening followed by ML surrogates to explore high-dimensional stochastic agent-based models and identify unstable regions.