Addressing Topic Granularity and Hallucination in Large Language Models for Topic Modelling

arXiv:2405.00611v1 Announce Type: new
Abstract: Large language models (LLMs) with their strong zero-shot topic extraction capabilities offer an alternative to probabilistic topic modelling and closed-set topic classification approaches. As zero-shot topic extractors, LLMs are expected to understand human instructions to generate relevant and non-hallucinated topics based on the given documents. However, LLM-based topic modelling approaches often face difficulties in generating topics with adherence to granularity as specified in human instructions, often resulting in many near-duplicate topics. Furthermore, methods for addressing …

abstract alternative arxiv capabilities classification cs.cl extraction generate hallucination human language language models large language large language models llms modelling set topics type zero-shot