- author = "Herbie Bradley and Honglu Fan and Theodoros Galanos and Ryan Zhou and Daniel Scott and Joel Lehman",
- title = "The {OpenELM} Library: Leveraging Progress in Language Models for Novel Evolutionary Algorithms",
- booktitle = "Genetic Programming Theory and Practice XX",
- year = "2023",
- editor = "Stephan Winkler and Leonardo Trujillo and Charles Ofria and Ting Hu",
- series = "Genetic and Evolutionary Computation",
- pages = "177--201",
- address = "Michigan State University, USA",
- month = jun # " 1-3",
- publisher = "Springer",
- keywords = "genetic algorithms, genetic programming",
- isbn13 = "978-981-99-8412-1",
-
DOI = "
10.1007/978-981-99-8413-8_10",
-
code_url = "
https://github.com/CarperAI/OpenELM",
- abstract = "in recent years, Large Language Models (LLMs) have rapidly progressed in their capabilities in natural language processing (NLP) tasks, which have interestingly grown in scope to include generating computer programs. Indeed, recent studies have demonstrated how LLMs can enable highly proficient genetic programming (GP) algorithms and novel evolutionary algorithms more broadly. Motivated by these opportunities, this paper introduces OpenELM, an open-source Python library for designing evolutionary algorithms that leverage LLMs to intelligently generate variation, as well as to assess fitness and measures of diversity. The library includes implementations of several variation operators, and is designed to accommodate those with limited compute resources, by enabling fast inference, being runnable through hosted notebooks (such as Google Colab), and allowing for API-based LLMs to be used instead of local models run on GPUs. Additionally, OpenELM includes a variety of domain implementations for easy experimentation and adaptation, including several GP domains. The hope is to help researchers easily develop new approaches and applications within the nascent and largely unexplored paradigm of evolutionary algorithms that leverage LLMs.",
-
notes = "
https://huggingface.co/CarperAI/
Part of \cite{Hu:2023:GPTP} published after the workshop in 2024",
