Fig.1

Concept

Semantic rubrics

Semantic rubrics are structured scoring criteria that judge the meaning and quality of an output rather than its surface form. Think of a grading rubric a human TA uses, except the grader is an LLM applying each criterion to a generated artifact.

The rest of “Semantic rubrics” is a premium feature: every concept in the library gets a precise, practitioner-focused write-up like this one, cross-linked straight from the paper summaries that use it.

Log in to unlock

← Back to the library

Semantic rubrics, explained · Fig. 1