SCRuB shows frontier LLMs outperform human experts across a five-dimensional critical thinking rubric for social concept reasoning, winning 80.8% of 1,170 pairwise expert judgments and indicating single-turn evaluation saturation.
Do not refer- ence the HLE dataset, the specific academic subfield, or any specialized terminology that would require domain expertise to understand
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
SCRuB: Social Concept Reasoning under Rubric-Based Evaluation
SCRuB shows frontier LLMs outperform human experts across a five-dimensional critical thinking rubric for social concept reasoning, winning 80.8% of 1,170 pairwise expert judgments and indicating single-turn evaluation saturation.