Relating the Seemingly Unrelated: Principled Understanding of Generalization for Generative Models in Arithmetic Reasoning Tasks

X Xu, Z Zhao, H Zhang, Y Yang - arxiv preprint arxiv:2407.17963, 2024 - arxiv.org
Large language models (LLMs) have demonstrated impressive versatility across numerous
tasks, yet their generalization capabilities remain poorly understood. To investigate these …

Beyond In-Distribution Success: Scaling Curves of CoT Granularity for Language Model Generalization

R Wang, W Huang, S Song, H Zhang… - arxiv preprint arxiv …, 2025 - arxiv.org
Generalization to novel compound tasks under distribution shift is important for deploying
transformer-based language models (LMs). This work investigates Chain-of-Thought (CoT) …