y0news
AnalyticsDigestsSourcesTopicsRSSAICrypto

#human-reasoning News & Analysis

1 article tagged with #human-reasoning. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

1 articles
AIBearisharXiv – CS AI · 6h ago6/10
🧠

RealMath-Eval: Why SOTA Judges Struggle with Real Human Reasoning

Researchers introduce RealMath-Eval, a benchmark revealing that state-of-the-art LLM judges fail to accurately evaluate authentic student mathematical reasoning, performing significantly worse on real exam responses (MSE ~2.96) than on synthetic LLM-generated solutions (MSE ~1.17). The study identifies an "Evaluation Gap" stemming from human errors occupying a more diverse semantic space than the predictable patterns found in synthetic errors.