Showing cs.CLShow all
2 papers · 1 filter
cs.CL2024
What Makes In-context Learning Effective for Mathematical Reasoning: A Theoretical Analysis
Jiayu Liu, Zhenya Huang, Chaokun Wang +3
Owing to the capability of in-context learning, large language models (LLMs) have shown impressive performance across diverse mathematical reasoning benchmarks. However, we find th…
cs.CL2024
Learning by Analogy: Enhancing Few-Shot Prompting for Math Word Problem Solving with Computational Graph-Based Retrieval
Xiaocong Yang, Jiacheng Lin, Ziqi Wang +1
Large language models (LLMs) are known to struggle with complicated reasoning tasks such as math word problems (MWPs). In this paper, we present how analogy from similarly structur…