Collapse of Self-trained Language Models

Published: 19 Mar 2024, Last Modified: 02 Apr 2024Tiny Papers @ ICLR 2024 NotableEveryoneRevisionsBibTeXCC BY 4.0
Keywords: LLM, self-train, dynamic eval, AI, large language models, GPT-2, model collapse
TL;DR: A paper on collapse of self-trained language models
Abstract: In various fields of knowledge creation, including science, new ideas often build on pre-existing information. In this work, we explore this concept within the context of language models. Specifically, we explore the potential of self-training models on their own outputs, akin to how humans learn and build on their previous thoughts and actions. While this approach is intuitively appealing, our research reveals its practical limitations. We find that extended self-training of the GPT-2 model leads to a significant degradation in performance, resulting in repetitive and collapsed token output.
Supplementary Material: zip
Submission Number: 120