@article{aligninglanguagemodelbenchmarkswithpairw, title = {Aligning Language Model Benchmarks with Pairwise Preferences}, author = {Marco Gutierrez and Xinyi Leng and Hannah Cyberey and Jonathan Richard Schwarz and Ahmed Alaa and Thomas Hartvigsen}, year = {2026}, eprint = {2602.02898}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2602.02898}, }