Pre-trained language models (pLMs) learn intricate patterns and contextual dependencies via unsupervised learning on vast text data, driving breakthroughs across NLP tasks. Despite these achievements, these models remain black boxes, necessitating research into understanding their decision-making processes. Recent studies explore representation analysis by clustering latent spaces within pre-trained models. However, these approaches are limited in terms of scalability and the scope of interpretation because of high computation costs of clustering algorithms. This study focuses on comparing clustering algorithms for the purpose of scaling encoded concept discovery of representations from pLMs. Specifically, we compare three algorithms in their capacity to unveil the encoded concepts through their alignment to human-defined ontologies: Agglomerative Hierarchical Clustering, Leaders Algorithm, and K-Means Clustering. Our results show that K-Means has the potential to scale to very large datasets, allowing rich latent concept discovery, both on the word and phrase level.

翻译：预训练语言模型通过在海量文本数据上进行无监督学习，习得复杂的模式与上下文依赖关系，推动了自然语言处理任务的突破性进展。然而，尽管取得这些成就，这些模型仍被视为黑箱，亟需对其决策过程的理解研究。近期工作通过聚类预训练模型中的潜在空间进行表征分析，但受限于聚类算法的高计算成本，这些方法在可扩展性和解释范围上存在局限。本研究聚焦于比较不同聚类算法，旨在扩展对预训练语言模型表征中编码概念的发现。具体而言，我们比较了三种算法在通过对齐人类定义本体论揭示编码概念方面的能力：凝聚层次聚类、领导者算法和K-Means聚类。结果表明，K-Means聚类具备扩展至超大规模数据集的潜力，能够在词汇和短语层面实现丰富的潜在概念发现。