Language Model Evolution: An Iterated Learning Perspective

arXiv:2404.04286v1 Announce Type: cross
Abstract: With the widespread adoption of Large Language Models (LLMs), the prevalence of iterative interactions among these models is anticipated to increase. Notably, recent advancements in multi-round self-improving methods allow LLMs to generate new examples for training subsequent models. At the same time, multi-agent LLM systems, involving automated interactions among agents, are also increasing in prominence. Thus, in both short and long terms, LLMs may actively engage in an evolutionary process. We draw parallels between the …

abstract adoption agent arxiv automated cs.ai cs.cl cs.lg evolution examples generate improving interactions iterative language language model language models large language large language models llm llms multi-agent perspective systems training type