SCRuB: Social Concept Reasoning under Rubric-Based Evaluation

📰 ArXiv cs.AI

arXiv:2605.06444v1 Announce Type: new Abstract: While many studies of Large Language Model (LLM) reasoning capabilities emphasize mathematical or technical tasks, few address reasoning about social concepts: the abstract ideas shaping social norms, culture, and institutions. This understudied capability is essential for modern models acting as social agents, yet no systematic evaluation methodology targets it. We introduce SCRuB (Social Concept Reasoning under Rubric-Based Evaluation), a framewo

Published 9 May 2026

Full Article

Title: SCRuB: Social Concept Reasoning under Rubric-Based Evaluation

Abstract:
arXiv:2605.06444v1 Announce Type: new Abstract: While many studies of Large Language Model (LLM) reasoning capabilities emphasize mathematical or technical tasks, few address reasoning about social concepts: the abstract ideas shaping social norms, culture, and institutions. This understudied capability is essential for modern models acting as social agents, yet no systematic evaluation methodology targets it. We introduce SCRuB (Social Concept Reasoning under Rubric-Based Evaluation), a framewo
Read full paper → ← Back to Reads