AI-Assisted Academic Text Refinement and Integrity Analysis for Ethical Scholarly Writing

We propose an AI-Assisted Academic Text Refinement and Integrity Analysis System designed to address the growing challenges of AI-generated content and plagiarism in scholarly writing. The system integrates natural language processing techniques to preprocess input texts, followed by a multi-faceted analysis that evaluates AI-likeness through linguistic features such as perplexity, lexical richness, and syntactic patterns. Furthermore, it employs web-based plagiarism detection using TF-IDF and cosine similarity to identify unoriginal content, thereby ensuring textual authenticity. If AI-generated or mixed-origin text is detected, the system applies advanced refinement techniques, including paraphrasing and tone enhancement, while preserving semantic integrity through validation using pre-trained language models. The proposed method also incorporates user management and submission tracking, enabling researchers to monitor their manuscript’s evolution and receive detailed reports with visualizations of AI-detection scores, plagiarism percentages, and readability improvements. Our contributions lie in the holistic integration of AI-detection, plagiarism screening, and humanization modules within a unified framework, which not only enhances ethical manuscript preparation but also provides actionable insights for academic writers. The system’s significance is underscored by its potential to foster academic integrity while adapting to the increasing prevalence of AI-assisted writing tools.

Authors

Institutions

Publication Details

Journal
Research Square
Published
2026-11-18
DOI
https://doi.org/10.21203/rs.3.rs-11419709/v1
Primary Topic
Academic integrity and plagiarism
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

AI-Assisted Academic Text Refinement and Integrity Analysis for Ethical Scholarly Writing

karunamurthy A
4 links
Research Square
Academic integrity and plagiarism
preprint

AI-Assisted Academic Text Refinement and Integrity Analysis for Ethical Scholarly Writing

karunamurthy A
preprint en

Abstract

We propose an AI-Assisted Academic Text Refinement and Integrity Analysis System designed to address the growing challenges of AI-generated content and plagiarism in scholarly writing. The system integrates natural language processing techniques to preprocess input texts, followed by a multi-faceted analysis that evaluates AI-likeness through linguistic features such as perplexity, lexical richness, and syntactic patterns. Furthermore, it employs web-based plagiarism detection using TF-IDF and cosine similarity to identify unoriginal content, thereby ensuring textual authenticity. If AI-generated or mixed-origin text is detected, the system applies advanced refinement techniques, including paraphrasing and tone enhancement, while preserving semantic integrity through validation using pre-trained language models. The proposed method also incorporates user management and submission tracking, enabling researchers to monitor their manuscript’s evolution and receive detailed reports with visualizations of AI-detection scores, plagiarism percentages, and readability improvements. Our contributions lie in the holistic integration of AI-detection, plagiarism screening, and humanization modules within a unified framework, which not only enhances ethical manuscript preparation but also provides actionable insights for academic writers. The system’s significance is underscored by its potential to foster academic integrity while adapting to the increasing prevalence of AI-assisted writing tools.

Research Square
Sri Manakula Vinayagar Educational Trust (IN), Sri Manakula Vinayagar Medical College and Hospital (IN)
Academic integrity and plagiarism
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon