Please Make it Sound like Human: Encoder-Decoder vs. Decoder-Only Transformers for AI-to-Human Text Style Transfer

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteur principal: Paneru, Utsav
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866910125686521856
author Paneru, Utsav
author_facet Paneru, Utsav
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2604_11687
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Please Make it Sound like Human: Encoder-Decoder vs. Decoder-Only Transformers for AI-to-Human Text Style Transfer
Paneru, Utsav
Computation and Language
I.2.7
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.
title Please Make it Sound like Human: Encoder-Decoder vs. Decoder-Only Transformers for AI-to-Human Text Style Transfer
topic Computation and Language
I.2.7
url https://arxiv.org/abs/2604.11687