Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.28832 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910267218067456 |
|---|---|
| author | Ding, Alex Rapaka, Tarun Rodriguez, Willy Yang, Jason |
| author_facet | Ding, Alex Rapaka, Tarun Rodriguez, Willy Yang, Jason |
| contents | Topic modeling is a branch of Natural Language Processing (NLP) that aims to organize large collections of texts into coherent groups according to word co-occurrence patterns, with Latent Dirichlet Allocation (LDA) remaining one of the most widely used and interpretable probabilistic approaches. Recent advances in NLP, particularly transformer-based language models, offer improved document representations. It is also known that the size of the model (in terms of number of parameters) has a significant impact in the performance of the language models on different pre-defined tasks. In this study, we systematically examine the effect of model size on topic quality by analyzing the performances of seven transformer-based language models (from small models such as MiniLM to large ones such as LLaMA-2) in a BERTopic pipeline on a variety of corpora. Topic quality is evaluated using coherence and divergence metrics following R{ö}der et al. (2015). Our results indicate that model size, ranging from 22 million to 13 billion parameters, has a negligible impact on the quality of the topic, suggesting that smaller models can achieve comparable performance to larger models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_28832 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | A comparative study of transformer-based embeddings for topic coherence Ding, Alex Rapaka, Tarun Rodriguez, Willy Yang, Jason Computation and Language Artificial Intelligence Topic modeling is a branch of Natural Language Processing (NLP) that aims to organize large collections of texts into coherent groups according to word co-occurrence patterns, with Latent Dirichlet Allocation (LDA) remaining one of the most widely used and interpretable probabilistic approaches. Recent advances in NLP, particularly transformer-based language models, offer improved document representations. It is also known that the size of the model (in terms of number of parameters) has a significant impact in the performance of the language models on different pre-defined tasks. In this study, we systematically examine the effect of model size on topic quality by analyzing the performances of seven transformer-based language models (from small models such as MiniLM to large ones such as LLaMA-2) in a BERTopic pipeline on a variety of corpora. Topic quality is evaluated using coherence and divergence metrics following R{ö}der et al. (2015). Our results indicate that model size, ranging from 22 million to 13 billion parameters, has a negligible impact on the quality of the topic, suggesting that smaller models can achieve comparable performance to larger models. |
| title | A comparative study of transformer-based embeddings for topic coherence |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2605.28832 |