AI-generated text has become common in academic and professional writing, prompting research into detection methods. Less studied is the reverse: systematically rewriting AI-generated prose to read as genuinely human-authored. We build a parallel corpus of 25,140 paired AI-input and human-reference text chunks, identify 11 measurable stylistic markers separating the two registers, and fine-tune three models: BART-base, BART-large, and Mistral-7B-Instruct with QLoRA. BART-large achieves the highest reference similarity -- BERTScore F1 of 0.924, ROUGE-L of 0.566, and chrF++ of 55.92 -- with 17x fewer parameters than Mistral-7B. We show that Mistral-7B's higher marker shift score reflects overshoot rather than accuracy, and argue that shift accuracy is a meaningful blind spot in current style transfer evaluation.

翻译：AI生成文本在学术和专业写作中已变得普遍，促使了对检测方法的研究。但逆向过程——系统性地将AI生成的散文改写得像真正人类所写——则研究较少。我们构建了一个包含25,140个配对AI输入与人类参考文本块的平行语料库，识别出11个可衡量的、区分两种语域的风格标记，并微调了三个模型：BART-base、BART-large和带有QLoRA的Mistral-7B-Instruct。BART-large达到了最高的参考相似度——BERTScore F1为0.924，ROUGE-L为0.566，chrF++为55.92——其参数量比Mistral-7B少17倍。我们证明，Mistral-7B更高的标记偏移分数反映的是过度调整而非准确性，并认为偏移准确性是当前风格迁移评估中一个有意义的盲点。