Pala Tej Deep, Panshul Sharma, Amir Zadeh 0001, Chuan Li, Soujanya Poria. Error Typing for Smarter Rewards: Improving Process Reward Models with Error-Aware Hierarchical Supervision. In Christos Christodoulopoulos 0001, Tanmoy Chakraborty 0002, Carolyn Rose, Violet Peng, editors, Findings of the Association for Computational Linguistics: EMNLP 2025, Suzhou, China, November 4-9, 2025. pages 14940-14954, Association for Computational Linguistics, 2025. [doi]
@inproceedings{DeepSZLP25,
title = {Error Typing for Smarter Rewards: Improving Process Reward Models with Error-Aware Hierarchical Supervision},
author = {Pala Tej Deep and Panshul Sharma and Amir Zadeh 0001 and Chuan Li and Soujanya Poria},
year = {2025},
url = {https://aclanthology.org/2025.findings-emnlp.807/},
researchr = {https://researchr.org/publication/DeepSZLP25},
cites = {0},
citedby = {0},
pages = {14940-14954},
booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2025, Suzhou, China, November 4-9, 2025},
editor = {Christos Christodoulopoulos 0001 and Tanmoy Chakraborty 0002 and Carolyn Rose and Violet Peng},
publisher = {Association for Computational Linguistics},
isbn = {979-8-89176-335-7},
}