Tell, Don't Show: Leveraging Language Models' Abstractive Retellings to Model Literary Themes
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918037728264192 |
|---|---|
| author | Lucy, Li Griffiths, Camilla Levine, Sarah Eberhardt, Jennifer L. Demszky, Dorottya Bamman, David |
| author_facet | Lucy, Li Griffiths, Camilla Levine, Sarah Eberhardt, Jennifer L. Demszky, Dorottya Bamman, David |
| contents | Conventional bag-of-words approaches for topic modeling, like latent Dirichlet allocation (LDA), struggle with literary text. Literature challenges lexical methods because narrative language focuses on immersive sensory details instead of abstractive description or exposition: writers are advised to "show, don't tell." We propose Retell, a simple, accessible topic modeling approach for literature. Here, we prompt resource-efficient, generative language models (LMs) to tell what passages show, thereby translating narratives' surface forms into higher-level concepts and themes. By running LDA on LMs' retellings of passages, we can obtain more precise and informative topics than by running LDA alone or by directly asking LMs to list topics. To investigate the potential of our method for cultural analytics, we compare our method's outputs to expert-guided annotations in a case study on racial/cultural identity in high school English language arts books. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_23166 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Tell, Don't Show: Leveraging Language Models' Abstractive Retellings to Model Literary Themes Lucy, Li Griffiths, Camilla Levine, Sarah Eberhardt, Jennifer L. Demszky, Dorottya Bamman, David Computation and Language Conventional bag-of-words approaches for topic modeling, like latent Dirichlet allocation (LDA), struggle with literary text. Literature challenges lexical methods because narrative language focuses on immersive sensory details instead of abstractive description or exposition: writers are advised to "show, don't tell." We propose Retell, a simple, accessible topic modeling approach for literature. Here, we prompt resource-efficient, generative language models (LMs) to tell what passages show, thereby translating narratives' surface forms into higher-level concepts and themes. By running LDA on LMs' retellings of passages, we can obtain more precise and informative topics than by running LDA alone or by directly asking LMs to list topics. To investigate the potential of our method for cultural analytics, we compare our method's outputs to expert-guided annotations in a case study on racial/cultural identity in high school English language arts books. |
| title | Tell, Don't Show: Leveraging Language Models' Abstractive Retellings to Model Literary Themes |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2505.23166 |