对比GPT-4.1在无上下文与微调下的文本简化效果
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
- 用提示工程实现无上下文简化，微调模型测试不同粒度表现
- gpt-4.1-mini无上下文在句级和文档级均表现稳定
- gpt-4.1-nano-ft在特定文档级任务中表现突出
本文介绍我们在CLEF 2025 SimpleText赛道任务1中的参赛方案，针对科学文本的句级和文档级简化问题。方法基于OpenAI的gpt-4.1、gpt-4.1-mini和gpt-4.1-nano模型，比较了两种策略：依赖提示工程的无上下文方法与跨模型的微调（FT）方法。gpt-4.1-mini在无上下文条件下，在句级与文档级简化任务中均表现出色；而微调模型结果参差不齐，凸显了不同粒度文本简化带来的复杂性。其中，gpt-4.1-nano-ft在某次文档级简化任务中表现尤为突出。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。