LLM-Guided Planning and Summary-Based Scientific Text Simplification: DS@GT at CLEF 2025 SimpleText

TL;DR

This paper introduces a two-stage LLM-based framework for scientific text simplification at sentence and document levels, utilizing planning and summaries to enhance coherence and fidelity.

Contribution

It presents a novel approach combining planning and summarization with LLMs for improved scientific text simplification.

Findings

Effective sentence-level simplification with plan-driven methods

Enhanced document simplification guided by summaries

Improved coherence and faithfulness in simplified texts

Abstract

In this paper, we present our approach for the CLEF 2025 SimpleText Task 1, which addresses both sentence-level and document-level scientific text simplification. For sentence-level simplification, our methodology employs large language models (LLMs) to first generate a structured plan, followed by plan-driven simplification of individual sentences. At the document level, we leverage LLMs to produce concise summaries and subsequently guide the simplification process using these summaries. This two-stage, LLM-based framework enables more coherent and contextually faithful simplifications of scientific text.