RD2BENCH: Toward Data-Centric Automatic R&D
By Haotian Chen, Xinjie Shen, Zeqi Ye, Xiao Yang, Xu Yang, Weiqing Liu, Jiang Bian
Rating
1271
Battle Count: 84
Relevance
8/10
The benchmark includes tasks related to implementing financial formulas and factors, which are directly applicable to quantitative trading research and development.
Implementation Complexity
7/10
Implementing the benchmark requires understanding of large language models, code generation, and specific domain knowledge in finance and machine learning.
Reproducibility
4/5
The paper provides detailed information on the benchmark setup and evaluation metrics, enhancing reproducibility.
About this paper
Methodology: Benchmarking. Problem types: Natural Language Processing, Code Generation, Formula Implementation, Model Architecture Implementation.
The interactive Everscope explorer (charts, battles, favorites) loads below.