LLM-Guided Planning and Summary-Based Scientific Text Simplification: DS@GT at CLEF 2025 SimpleText
This addresses the problem of making scientific texts more accessible for general audiences, though it appears incremental as it builds on existing LLM-based approaches.
The paper tackled scientific text simplification at both sentence and document levels by using large language models to generate structured plans and summaries, then guiding simplification based on these, resulting in more coherent and contextually faithful outputs.
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.