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

Utsav Paneru
4/13/2026
cs.CL
transformer-attention

No confident code implementation found for this paper. 2 possible matches can be shown below.

Abstract

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.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 2 weaker matches are hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Can You Make It Sound Like You? Post-Editing LLM-Generated Text for Personal Style

85% match2026

Operation-Guided Progressive Human-to-AI Text Transformation Benchmark for Multi-Granularity AI-Text Detection

83% match1 repo102026

Likelihood Is Not Authorship: Can We Reliably Measure Human Contribution in AI-Assisted Writing?

83% match2026

Style as a Confound: False Positives in AI Detection of Non-Native Academic Writing

82% match2026

Predicting Steering Vectors and Adapter Weights for Few-Shot Author-Style Transfer

82% match2026

Voice Under Revision: Large Language Models and the Normalization of Personal Narrative

82% match2026

Cite this paper

@article{paneru2026please,
  title  = {Please Make it Sound like Human: Encoder-Decoder vs. Decoder-Only Transformers for AI-to-Human Text Style Transfer},
  author = {Utsav Paneru},
  year   = {2026},
  eprint = {2604.11687},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2604.11687v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2604.11687.svg)](https://codeofpaper.com/paper/2604.11687)

Discussion