WIMPE factorizes reference answers into weighted context-bound points and applies alignment (WPA) and conflict penalty (PCP) metrics, yielding higher human correlation than prior rubric or checklist methods across 10 generative tasks.
The larger the weight, the more important the scoring point is
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
-
Judge Like Human Examiners: A Weighted Importance Multi-Point Evaluation Framework for Generative Tasks with Long-form Answers
WIMPE factorizes reference answers into weighted context-bound points and applies alignment (WPA) and conflict penalty (PCP) metrics, yielding higher human correlation than prior rubric or checklist methods across 10 generative tasks.