UM_FHS at the CLEF 2025 SimpleText Track: Comparing No-Context and Fine-Tune Approaches for GPT-4.1 Models in Sentence and Document-Level Text Simplification

TL;DR

This paper compares no-context prompt engineering and fine-tuning approaches using GPT-4.1 models for scientific text simplification at sentence and document levels, highlighting the strengths and challenges of each method.

Contribution

It introduces a comparative analysis of no-context versus fine-tuned GPT-4.1 models for text simplification in scientific documents, emphasizing model performance differences.

Findings

gpt-4.1-mini no-context performs well at both levels

fine-tuned models show mixed results depending on the task

gpt-4.1-nano-ft excels at document-level simplification in one case

Abstract

This work describes our submission to the CLEF 2025 SimpleText track Task 1, addressing both sentenceand document-level simplification of scientific texts. The methodology centered on using the gpt-4.1, gpt-4.1mini, and gpt-4.1-nano models from OpenAI. Two distinct approaches were compared: a no-context method relying on prompt engineering and a fine-tuned (FT) method across models. The gpt-4.1-mini model with no-context demonstrated robust performance at both levels of simplification, while the fine-tuned models showed mixed results, highlighting the complexities of simplifying text at different granularities, where gpt-4.1-nano-ft performance stands out at document-level simplification in one case.