对比微调与提示工程在文本简化中的效果，发现微调更优。
Simplify-This: A Comparative Analysis of Prompt-Based and Fine-Tuned LLMs
- 用多个基准测试比较微调与提示工程方法
- 微调模型结构简化更强，提示法语义相似度更高但易复制原文
- 人工评估支持微调输出整体更优，适合需高质量简化的场景
大型语言模型（LLMs）具备强大的文本生成能力，但在微调与提示工程之间存在实际权衡。我们提出Simplify-This，一项针对编码器-解码器型LLM在文本简化任务上的对比研究，涵盖多个基准测试和多种评估指标。结果表明，微调模型在结构简化方面表现更优，而提示方法虽在语义相似度上得分更高，但倾向于直接复制输入内容。人工评估显示微调输出整体更受青睐。我们公开了代码、清洗后的衍生数据集、微调模型检查点及提示模板，以促进可复现性与后续研究。
原文摘要 · Abstract (English)
Large language models (LLMs) enable strong text generation, and in general there is a practical tradeoff between fine-tuning and prompt engineering. We introduce Simplify-This, a comparative study evaluating both paradigms for text simplification with encoder-decoder LLMs across multiple benchmarks, using a range of evaluation metrics. Fine-tuned models consistently deliver stronger structural simplification, whereas prompting often attains higher semantic similarity scores yet tends to copy inputs. A human evaluation favors fine-tuned outputs overall. We release code, a cleaned derivative dataset used in our study, checkpoints of fine-tuned models, and prompt templates to facilitate reproducibility and future work.
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。