RUM is a rule-plus-LLM grader for software testing work that matches human scores on most dimensions while cutting grading time and cost.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SE 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
RUM: Rule+LLM-Based Comprehensive Assessment on Testing Skills
RUM is a rule-plus-LLM grader for software testing work that matches human scores on most dimensions while cutting grading time and cost.