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.
@article{arxiv.2603.23532,
title = {Generating Hierarchical JSON Representations of Scientific Sentences Using LLMs},
author = {Satya Sri Rajiteswari Nimmagadda and Ethan Young and Niladri Sengupta and Ananya Jana and Aniruddha Maiti},
journal= {arXiv preprint arXiv:2603.23532},
year = {2026}
}
Comments
accepted to 21th International Conference on Semantic Computing (IEEE ICSC 2026)