Abstract:The recent success of large pre-trained language models (PLMs) has motivated their integration into topic modeling. However, PLM-augmented topic models differ from classical co-occurrence models such as Latent Dirichlet Allocation (LDA) not only in performance, but also in the type of semantic structure they capture. We formalize this distinction along two psycholinguistic axes: thematic relatedness (dog/bone) and taxonomic similarity (dog/wolf). To measure both axes over topic words, we construct a large synthetic benchmark of word pairs using LLM-based annotation and train a neural scorer on it. Across multiple corpora and model families, the scorer places different topic-model families at distinct positions within the joint similarity-relatedness space. The two scores further predict downstream task performance: tasks requiring similarity benefit from similarity-rich topics, whereas tasks requiring relatedness benefit from the converse, and excessive emphasis on either axis degrades performance on tasks aligned with the opposing semantic structure. Neither axis is uniformly beneficial. Measuring both therefore provides a practical, model-agnostic diagnostic for evaluating the semantic structure captured by topic models.
| Comments: | 26 pages, 9 figures, 18 tables |
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2603.10619 [cs.CL] |
| (or arXiv:2603.10619v2 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2603.10619 arXiv-issued DOI via DataCite |
Submission history
From: Hanlin Xiao [view email]
[v1]
Wed, 11 Mar 2026 10:27:43 UTC (3,607 KB)
[v2]
Mon, 1 Jun 2026 09:21:03 UTC (1,313 KB)