When Numbers Tell Half the Story: Human-Metric Alignment in Topic Model Evaluation

Thibault Prouteau, Francis Lareau, Nicolas Dugue, Jean-Charles Lamirel, Christophe Malaterre


Abstract
Topic models uncover latent thematic structures in text corpora, yet evaluating their quality remains challenging, particularly in specialized domains. Existing methods often rely on automated metrics like topic coherence and diversity, which may not fully align with human judgment. Human evaluation tasks, such as word intrusion, provide valuable insights but are costly and primarily validated on general-domain corpora. This paper introduces Topic Word Mixing (TWM), a novel human evaluation task assessing inter-topic distinctness by testing whether annotators can distinguish between word sets from single or mixed topics. TWM complements word intrusion’s focus on intra-topic coherence and provides a human-grounded counterpart to diversity metrics. We evaluate six topic models–both statistical and embedding-based (LDA, NMF, Top2Vec, BERTopic, CFMF, CFMF-emb)–comparing automated metrics with human evaluation methods based on nearly 4,000 annotations from a domain-specific corpus of philosophy of science publications. Our findings reveal that word intrusion and coherence metrics do not always align, particularly in specialized domains, and that TWM captures human-perceived distinctness while appearing to align with diversity metrics. We release the annotated dataset and task generation code. This work highlights the need for evaluation frameworks bridging automated and human assessments, particularly for domain-specific corpora.
Anthology ID:
2026.lrec-1.474
Volume:
Proceedings of the Fifteenth Language Resources and Evaluation Conference
Month:
May
Year:
2026
Address:
Palma de Mallorca, Spain
Editors:
Stelios Piperidis, Núria Bel, Henk van den Heuvel, Nancy Ide, Simon Krek, Antonio Toral
Venue:
LREC
SIG:
Publisher:
ELRA Language Resource Association
Note:
Pages:
5970–5980
Language:
External URL:
https://lrec.elra.info/lrec2026-main-474
DOI:
10.63317/387fiwstpipw
Bibkey:
Cite (ACL):
Thibault Prouteau, Francis Lareau, Nicolas Dugue, Jean-Charles Lamirel, and Christophe Malaterre. 2026. When Numbers Tell Half the Story: Human-Metric Alignment in Topic Model Evaluation. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 5970–5980, Palma de Mallorca, Spain. ELRA Language Resource Association.
Cite (Informal):
When Numbers Tell Half the Story: Human-Metric Alignment in Topic Model Evaluation (Prouteau et al., LREC 2026)
Copy Citation:
Optionalsupplementarymaterial:
 2026.lrec-1.474.OptionalSupplementaryMaterial.zip