EDIT improves LLM rubric grading faithfulness by diagnosing problematic reasoning steps via posterior belief and grounding scores then applying local SFT revisions and belief-penalizing RL.
Calibrating LLM s with Preference Optimization on Thought Trees for Generating Rationale in Science Question Scoring
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
EDIT: Evidence-Diagnosed Intervention Training for Rule-Faithful LLM Grading
EDIT improves LLM rubric grading faithfulness by diagnosing problematic reasoning steps via posterior belief and grounding scores then applying local SFT revisions and belief-penalizing RL.