RESEARCHInvestigateNEXT 12 MONTHS
ExecRubrics: Executable Tool-Augmented Rubrics for Verifiable and Efficient Long-Form Evaluation
arXiv cs.CL — Computation and Language
Factual evidence
What the source reports
ExecRubrics proposes executable code-based rubrics to replace ambiguous natural-language LLM judges for long-form evaluations.
Open source