AIBullisharXiv – CS AI · 5d ago6/104
🧠
Reliable Fine-Grained Evaluation of Natural Language Math Proofs
Researchers have developed ProofGrader, a new AI system that can reliably evaluate natural language mathematical proofs generated by large language models on a fine-grained 0-7 scale. The system was trained using ProofBench, the first expert-annotated dataset of proof ratings covering 145 competition math problems and 435 LLM solutions, achieving significant improvements over basic evaluation methods.