@article{posthocrewardcalibrationacasestudyon, title = {Post-hoc Reward Calibration: A Case Study on Length Bias}, author = {Zeyu Huang and Zihan Qiu and Zili Wang and Edoardo M. Ponti and Ivan Titov}, year = {2024}, eprint = {2409.17407}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2409.17407v1}, }