Collapse of Self-trained Language Models
This addresses a potential pitfall in AI training methods for researchers and practitioners, showing that self-training can be harmful rather than beneficial.
The paper investigates self-training language models on their own outputs, finding that extended self-training of GPT-2 leads to significant performance degradation, with repetitive and collapsed token output.
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.