Student or educator? Sign up with your school email and get 6 months of Pro free.
Cited by 27Academic integrity and plagiarismArtificial Intelligence in EducationEthics and Social Impacts of AI

The DOI matches its Crossref record; 34 of the 34 references it cites were found in a registry or an index; 127 of the 149 sources its claims cite were checked for support.

Evaluating the Effectiveness and Ethical Implications of AI Detection Tools in Higher Education

Open access

Published version of a preprint

Abstract

The rapid rise of generative AI tools such as ChatGPT has prompted significant shifts in how higher education institutions approach academic integrity. Many universities have implemented AI detection tools like Turnitin AI, GPTZero, Copyleaks, and ZeroGPT to identify AI-generated content in student work. This qualitative evidence synthesis draws on peer-reviewed journal articles published between 2021 and 2024 to evaluate the effectiveness, limitations, and ethical implications of AI detection tools in academic settings. While AI detectors offer scalable solutions, they frequently produce false positives and lack transparency, especially for multilingual or non-native English speakers. Ethical concerns surrounding surveillance, consent, and fairness are central to the discussion. The review also highlights gaps in institutional policies, inconsistent enforcement, and limited faculty training. It calls for a shift away from punitive approaches toward AI-integrated pedagogies that emphasize ethical use, student support, and inclusive assessment design. Emerging innovations such as watermarking and hybrid detection systems are discussed, though implementation challenges persist. Overall, the findings suggest that while AI detection tools play a role in preserving academic standards, institutions must adopt balanced, transparent, and student-centered strategies that align with evolving digital realities and uphold academic integrity without compromising rights or equity.

Overview

CoChat Summary

TL;DR

This narrative literature review synthesizes 24 peer-reviewed studies (2021–2024) on AI detection tools in higher education, concluding that detectors are unreliable, frequently produce false positives (especially for non-native English speakers), and are often deployed without transparency or consent. The authors call for a shift from punitive detection toward AI-integrated pedagogy, inclusive assessment redesign, and clearer institutional policy.

Key findings

  • Detection accuracy is inconsistent and degrades against newer models: detectors performed well on ChatGPT-3.5 output but poorly on GPT-4 output, and paraphrasing with DIPPER dropped DetectGPT accuracy from 70.3% to 4.6% at a fixed 1% false positive rate. In one evaluation of ten free tools against ChatGPT-3.5 content and its paraphrased versions, only five detected original AI content error-free, with accuracy ranging from 0% to 100%; Sapling and Undetectable AI showed 100% accuracy even after paraphrasing.
  • False positives disproportionately threaten non-native English speakers and students using formal or polished prose; Turnitin advises against integrity decisions based solely on AI detection scores when the likelihood of AI authorship is under 40%.
  • Human judgment is also weak: ESL instructors were only 33%–66% correct in identifying whether texts were student- or AI-written, and in an Oxford Old English poetry comparison, AI essays averaged 60.46 versus 63.57 for human essays (difference not statistically significant, p = 0.10), while Quillbot reached 95.59% detection accuracy.
  • Ethical and procedural problems are pervasive: tools are typically deployed without informed consent or transparency, some retain student data indefinitely or train models on it, and 87% of surveyed students showed inadequate comprehension of AI misuse ramifications. Institutions lack standardized procedures, appeal mechanisms, and evidence standards.

Methods

  • Design: narrative literature review, justified via interpretivist/subjectivist paradigms and methodological flexibility; appraised using SANRA criteria (six items, 0–2 each, total 12; original validation Cronbach's α = 0.68, ICC = 0.77) and documented with a PRISMA-ScR flow diagram.
  • Data: peer-reviewed English-language articles published 2021–2024 from ERIC, EBSCOhost, and JSTOR, restricted to higher education settings and tool-specific content (Turnitin AI, GPTZero, Copyleaks, ZeroGPT, CrossPlag, OpenAI classifiers); the initial search yielded 128 records, with 24 studies included after screening.
  • Analysis: qualitative thematic analysis yielding three inductively derived domains aligned to three research questions — institutional policy/implementation, detection accuracy and system performance, and ethical/pedagogical implications.

Limitations

  • Stated by the authors: the narrative design lacks the systematic rigor and transparency of scoping/systematic reviews, is vulnerable to subjectivity and selective interpretation, and has limited reproducibility; database coverage excluded Scopus, Web of Science, IEEE, and institutional policy documents, reducing generalizability; no interrater validation or structured thematic coding was used; SANRA was used as a guiding framework without explicit scoring or comparative quality tables; the review covered only text-based detection, excluding code, audio, and multimedia; and no explicit theoretical frameworks (e.g., academic integrity theory, surveillance ethics, technology acceptance models) were applied, so the review should be regarded as exploratory rather than definitive.
  • Evident from the text: several reported figures are drawn from secondary citations of other studies rather than independent testing by the authors, and the abstract and conclusions sections appear in the provided text in a fragmented, out-of-order form, with some sections (e.g., 1.2, 4.3.3, 5) split across multiple locations.

Model-written summary. Check it against the paper before relying on it.

Integrity signals

Registry

Crossref · 10.3390/info16100905

Cites

34 of 34 references verified0 citation errors · 0 not checkable

Statistics

Nothing to recompute.

Verification

Claims the paper makes

118 Valid · 8 Not valid · 20 Not checked · 41 Own results and interpretations

69 more claims · 50 with their cited sources checked

Create a free account to see all 187 claims and every source verdict.

See all claims — free account
  • Borderline: one of the tests for a substantial claim is unclear. 1
  • Probably not a substantial claim. 55
  • It may state two separate claims as one. 76
  • The quote only partly states this claim. 1

Create a free account to see these claims.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

Each contradiction between two passages listed here was confirmed by an independent check.

4 of 4

Citations

Cites

Show all 25 references

Cited by

See all 27

Metadata

Authors
Deep, P. D., Edgington, W. D., Ghosh, N., & Rahaman, M. S.
Affiliations
Sam Houston State University (US)
Venue
Information
Publisher
MDPI AG
Published
2025-10-16
Volume
16
Issue
10
Pages
905
ISSN
2078-2489 (ISSN-L)
OpenAlex
W4415282254
Cited by
26
References
25
Citations by year
2026: 26
FWCI
26.76
Type
journal article
Language
en
Open access
Locations
  • Information (publishedVersion, cc-by)
  • Preprints.org (acceptedVersion, cc-by)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Topics
  • Social Sciences › Education › Academic integrity and plagiarism
  • Social Sciences › Education › Artificial Intelligence in Education
  • Physical Sciences › Computer Science › Artificial Intelligence › Ethics and Social Impacts of AI
Keywords
AI detection tools, academic integrity, generative AI, higher education, AI-generated content, false positives, ethical implications, surveillance, student consent, fairness, institutional policy, faculty training, watermarking, multilingual learners, non-native English speakers, inclusive assessment, student-centered approach

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

The claim verdicts this report counts are experimental: their accuracy is not yet measured.

A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).

A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).

Cited sources are checked with a language model’s help (gpt-6-sol).

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Evaluating the Effectiveness and Ethical Implications of AI Detection Tools in Higher Education. https://app.cochat.ai/papers/10.3390/info16100905
The paper
Deep, P. D., Edgington, W. D., Ghosh, N., & Rahaman, M. S. (2025). Evaluating the Effectiveness and Ethical Implications of AI Detection Tools in Higher Education. Information. https://doi.org/10.3390/info16100905

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.