As conventional topic models rely on word co-occurrence to infer latent
topics, topic modeling for short texts has been a long-standing challenge.
Large Language Models (LLMs) can potentially overcome this challenge by
contextually learning the semantics of words via pretraining. This paper
studies two approaches, parallel prompting and sequential prompting, to use
LLMs for topic modeling. Due to the input length limitations, LLMs cannot
process many texts at once. By splitting the texts into smaller subsets and
processing them parallelly or sequentially, an arbitrary number of texts can be
handled by LLMs. Experimental results demonstrated that our methods can
identify more coherent topics than existing ones while maintaining the
diversity of the induced topics. Furthermore, we found that the inferred topics
adequately covered the input texts, while hallucinated topics were hardly
generated.

通过使用大型语言模型 (LLMs) 进行主题建模的两种方法，即并行提示和顺序提示，本文克服了传统主题模型在短文本上推断潜在主题时面临的挑战，并证明这些方法能够识别出比现有方法更连贯的主题，同时保持引发主题的多样性。此外，本研究发现所推断的主题充分涵盖了输入文本，而几乎没有产生虚构的主题。