一作ACL 2026Poster· Natural Language Processing
What Makes a Good Curriculum? Disentangling the Effects of Data Ordering on LLM Mathematical Reasoning
Yaning Jia · Chunhui Zhang · Xingjian Diao · Xiangchi Yuan · Zhongyu Ouyang · Chiyu Ma · Soroush Vosoughi
摘要
Curriculum learning (CL), which orders training data from easy to hard, has become a popular strategy for improving reasoning in large language models (LLMs). Yet prior work employs disparate difficulty metrics and training setups, leaving open fundamental questions: When does curriculum help? Wh...