LLM Merging methods for reasoning Tasks
收藏DataCite Commons2026-03-08 更新2026-05-04 收录
下载链接：
https://orkg.org/comparison/R1587743
下载链接
链接失效反馈官方服务：
资源简介：
This table analyzes LLM merging approaches targeting reasoning tasks, including benchmarks such as GSM8K, Common-sense and MATH. It examines their fusion mechanisms, architectural assumptions, training dependencies, and computational cost, clarifying how different merging paradigms impact multi-step logical and quantitative reasoning performance.
提供机构：
Open Research Knowledge Graph
创建时间：
2026-03-08
