paper-with-me

Papers

Generating Hierarchical JSON Representations of Scientific Sentences Using LLMs

2026-03-08 · Satya Sri Rajiteswari Nimmagadda, Ethan Young, Niladri Sengupta, Ananya Jana, Aniruddha Maiti arxiv

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.

📄 PDF Abstract BibTeX arXiv:2603.23532

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Structured information extraction from complex scientific text with fine-tuned large language models

2022-12-10 · Alexander Dunn, John Dagdelen, Nicholas Walker, SangHoon Lee 외

Intelligently extracting and linking complex scientific information from unstructured text is a challenging endeavor particularly for those inexperienced with natural language processing. Here, we present a simple sequen…

Language ModelingLanguage ModellingLarge Language Modelnamed-entity-recognition+3

Molecular Representations for Large Language Models

2026-05-03 · Nicholas T. Runcie, Fergus Imrie, Charlotte M. Deane arxiv

Large Language Models (LLMs) are increasingly being used to support scientific discovery. In chemistry, tasks such as reaction prediction and structure elucidation require reasoning about the structures of molecules. As …

Text Generation from Knowledge Graphs with Graph Transformers

2019-04-04 · NAACL 2019 6 · Rik Koncel-Kedziorski, Dhanush Bekal, Yi Luan, Mirella Lapata 외

Generating texts which express complex ideas spanning multiple sentences requires a structured representation of their content (document plan), but these representations are prohibitively expensive to manually produce. I…

DecoderDialogue GenerationKG-to-Text GenerationKnowledge Graphs+2

DeepJSONEval: Benchmarking Complex Nested JSON Data Mining for Large Language Models

2025-09-30 · Zhicheng Zhou, Jing Li, Suming Qiu, Junjie Huang 외 arxiv

The internet is saturated with low-density, high-redundancy information, such as social media comments, repetitive news, and lengthy discussions, making it difficult to extract valuable insights efficiently. Multi-layer …

Pretrained Language Models for Sequential Sentence Classification

2019-09-09 · IJCNLP 2019 11 · Arman Cohan, Iz Beltagy, Daniel King, Bhavana Dalvi 외

As a step toward better document-level understanding, we explore classification of a sequence of sentences into their corresponding categories, a task that requires understanding sentences in context of the document. Rec…

ClassificationGeneral ClassificationSentenceSentence Classification