2026
QEDBench: Quantifying the Alignment Gap in Automated Evaluation of University-Level Mathematical Proofs
Santiago Gonzalez, Alireza Amiribavandpour, Peter Ye, Edward Zhang, Ruslans Aleksejevs, Todor Antić +45
ICML 2026poster
As Large Language Models (LLMs) saturate elementary benchmarks, the research frontier has shifted from generation to the reliability of automated evaluation. We demonstrate that standard "LLM-as-a-Judge" protocols suffer from a systematic evaluation Alignment Gap when applied to upper-undergraduate …