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
This work addresses text simplification for scientific communication, but it is incremental, focusing on comparing existing methods on a specific benchmark.
The paper tackled sentence- and document-level simplification of scientific texts using GPT-4.1 models, finding that the no-context gpt-4.1-mini performed robustly while fine-tuned models had mixed results, with gpt-4.1-nano-ft excelling in one document-level case.
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.