Generating Hierarchical JSON Representations of Scientific Sentences Using LLMs
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911542862151680 |
|---|---|
| author | Nimmagadda, Satya Sri Rajiteswari Young, Ethan Sengupta, Niladri Jana, Ananya Maiti, Aniruddha |
| author_facet | Nimmagadda, Satya Sri Rajiteswari Young, Ethan Sengupta, Niladri Jana, Ananya Maiti, Aniruddha |
| contents | This paper investigates whether structured representations can preserve the meaning of scientific sentences. To test this, a lightweight LLM is fine-tuned using a novel structural loss function to generate hierarchical JSON structures from sentences collected from scientific articles. These JSONs are then used by a generative model to reconstruct the original text. Comparing the original and reconstructed sentences using semantic and lexical similarity we show that hierarchical formats are capable of retaining information of scientific texts effectively. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_23532 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Generating Hierarchical JSON Representations of Scientific Sentences Using LLMs Nimmagadda, Satya Sri Rajiteswari Young, Ethan Sengupta, Niladri Jana, Ananya Maiti, Aniruddha Computation and Language Artificial Intelligence This paper investigates whether structured representations can preserve the meaning of scientific sentences. To test this, a lightweight LLM is fine-tuned using a novel structural loss function to generate hierarchical JSON structures from sentences collected from scientific articles. These JSONs are then used by a generative model to reconstruct the original text. Comparing the original and reconstructed sentences using semantic and lexical similarity we show that hierarchical formats are capable of retaining information of scientific texts effectively. |
| title | Generating Hierarchical JSON Representations of Scientific Sentences Using LLMs |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2603.23532 |