Generating Hierarchical JSON Representations of Scientific Sentences Using LLMs
Abstract
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.
Fields of Study & Subjects
Natural Language Processing Techniques
Topic Modeling
Biomedical Text Mining and Ontologies
Publication details
- Journal / source
- 2026 International Conference on Semantic Computing (ICSC)
- Publisher
- IEEE
- Pages
- 218–220
- Publication date
- 2 February 2026