arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2404.02305cs.CLcs.AI
收藏

自训练语言模型的崩溃

Collapse of Self-trained Language Models

Czech Technical University in Prague(布拉格捷克技术大学)

David Herel, Tomas Mikolov

AI总结:

本文研究语言模型基于自身输出进行自训练的现象,发现对 GPT-2 延长自训练会造成性能显著下降,并产生重复、崩溃的 token 输出。

摘要:

在包括科学在内的各种知识创造领域,新思想往往建立在已有信息之上。在本研究中,我们在语言模型的语境下探索这一概念。具体而言,我们探索模型基于自身输出进行自训练的潜力,这类似于人类如何学习并依托其先前的思想和行动。尽管这种方法在直觉上很有吸引力,但我们的研究揭示了其实际局限性。我们发现,对 GPT-2 模型进行延长的自训练会导致性能显著下降,造成重复且崩溃的 token 输出。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑