cs.CLMar 8, 2026

Generating Hierarchical JSON Representations of Scientific Sentences Using LLMs

Authors: Satya Sri Rajiteswari Nimmagadda, Ethan Young, Niladri Sengupta, Ananya Jana, Aniruddha Maiti

Organizations: Marshall University · Fractal Analytics Inc · West Virginia State University

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.

Figures & tables

Explore similar work

CardsList
  1. .tmu: A Low-Entropy Tree-Structured Representation for LLM-Assisted Scientific Writing

    Mar 3, 2026Tianyou Liu, Ziqiang Li, Xurui Liu +2AI-Assisted Scientific ResearchLLM Training

  2. Structure Tax: How Structured Output affects LLMs Performance

    Oct 8, 2026Vineet Kumar, Kanishka, Bhuvanesh MandoraStructured Output GenerationStructured Reasoning in Language Models

  3. SciZoom: A Large-scale Benchmark for Hierarchical Scientific Summarization across the LLM Era

    Mar 17, 2026Han Jang, Junhyeok Lee, Kyu Sung ChoiLLM EvaluationScientific Communication