From Scoring to Explanations: Evaluating SHAP and LLM Rationales for Rubric-based Teaching Quality Assessment

This research proposes a framework for sentence-level interpretability in rubric-based scoring, combining Shapley-value attributions with rationales from large language models (LLMs). It compares fine-tuned language models and prompted LLMs for teaching quality assessment, finding PLMs offer better prediction accuracy despite label compression.