@article{predictingdisagreementwithhumanratersinl, title = {Predicting Disagreement with Human Raters in LLM-as-a-Judge Difficulty Assessment without Using Generation-Time Probability Signals}, author = {Yo Ehara}, year = {2026}, eprint = {2605.12422}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2605.12422}, }