A 100-problem benchmark of difficult math derivations from academic papers, where the best LLMs score below 5% and small-scale fine-tuning yields modest gains on standard math benchmarks.
What are the preconditions?
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
STORM-BORN: A Challenging Mathematical Derivations Dataset Curated via a Human-in-the-Loop Multi-Agent Framework
A 100-problem benchmark of difficult math derivations from academic papers, where the best LLMs score below 5% and small-scale fine-tuning yields modest gains on standard math benchmarks.