Work

On the Information Retention Capabilities of Hierarchical JSON Representations of Scientific Texts

Year: 2026

Type: article

Abstract: This paper studies whether structured representations can retain the meaning contained in scientific sentences. A lightweight LLM is fine-tuned to generate JSON structures from scientific sentences. The objective was to capture information contained in the sentence using a hierarchical structure. The structured representations are then used to reconstruct sentences with a generative model to test whether such representations are useful to retain the meaning of the sentence. The evaluation compares the reconstructed sentences with the originals using semantic and lexical similarity. Our results show that hierarchical structured formats preserve semantic information with an average cosine similarity of 0.87.

Source: Big Data and Cognitive Computing

DOI: 10.3390/bdcc10090288

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

Institutions: Marshall University, West Virginia State University

Language: English

Topic: Topic Modeling

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: gold

Estimated APC paid: $2,172

Funder: National Aeronautics and Space Administration