When Large Language Models Meet Evolutionary Algorithms: Potential Enhancements and Challenges

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Chao, Zhao, Jiaxuan, Jiao, Licheng, Li, Lingling, Liu, Fang, Yang, Shuyuan
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910861757513728
author Wang, Chao
Zhao, Jiaxuan
Jiao, Licheng
Li, Lingling
Liu, Fang
Yang, Shuyuan
author_facet Wang, Chao
Zhao, Jiaxuan
Jiao, Licheng
Li, Lingling
Liu, Fang
Yang, Shuyuan
contents Pre-trained large language models (LLMs) exhibit powerful capabilities for generating natural text. Evolutionary algorithms (EAs) can discover diverse solutions to complex real-world problems. Motivated by the common collective and directionality of text generation and evolution, this paper first illustrates the conceptual parallels between LLMs and EAs at a micro level, which includes multiple one-to-one key characteristics: token representation and individual representation, position encoding and fitness shaping, position embedding and selection, Transformers block and reproduction, and model training and parameter adaptation. These parallels highlight potential opportunities for technical advancements in both LLMs and EAs. Subsequently, we analyze existing interdisciplinary research from a macro perspective to uncover critical challenges, with a particular focus on evolutionary fine-tuning and LLM-enhanced EAs. These analyses not only provide insights into the evolutionary mechanisms behind LLMs but also offer potential directions for enhancing the capabilities of artificial agents.
format Preprint
id arxiv_https___arxiv_org_abs_2401_10510
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle When Large Language Models Meet Evolutionary Algorithms: Potential Enhancements and Challenges
Wang, Chao
Zhao, Jiaxuan
Jiao, Licheng
Li, Lingling
Liu, Fang
Yang, Shuyuan
Neural and Evolutionary Computing
Artificial Intelligence
Computation and Language
Machine Learning
Pre-trained large language models (LLMs) exhibit powerful capabilities for generating natural text. Evolutionary algorithms (EAs) can discover diverse solutions to complex real-world problems. Motivated by the common collective and directionality of text generation and evolution, this paper first illustrates the conceptual parallels between LLMs and EAs at a micro level, which includes multiple one-to-one key characteristics: token representation and individual representation, position encoding and fitness shaping, position embedding and selection, Transformers block and reproduction, and model training and parameter adaptation. These parallels highlight potential opportunities for technical advancements in both LLMs and EAs. Subsequently, we analyze existing interdisciplinary research from a macro perspective to uncover critical challenges, with a particular focus on evolutionary fine-tuning and LLM-enhanced EAs. These analyses not only provide insights into the evolutionary mechanisms behind LLMs but also offer potential directions for enhancing the capabilities of artificial agents.
title When Large Language Models Meet Evolutionary Algorithms: Potential Enhancements and Challenges
topic Neural and Evolutionary Computing
Artificial Intelligence
Computation and Language
Machine Learning
url https://arxiv.org/abs/2401.10510