AI News HubLIVE
Original source2 min read

Sem-Detect: Semantic Level Detection of AI Generated Peer-Reviews

A new method, Sem-Detect, distinguishes human-written peer reviews from AI-generated ones by combining textual features with claim-level semantic analysis. It leverages the observation that different AI models converge on similar points while human reviewers are more diverse. On over 20,000 reviews from ICLR and NeurIPS, it improves [email protected]% FPR by 25.5% in binary setting. In three-class scenario, fewer than 3.5% of LLM-refined human reviews are misclassified as AI-generated.

SourcearXiv Computational LinguisticsAuthor: Andr\'e V. Duarte, Brian Tufts, Aditya Oke, Fei Fang, Arlindo L. Oliveira, Lei Li

[2605.21713] Sem-Detect: Semantic Level Detection of AI Generated Peer-Reviews

[Submitted on 20 May 2026]

Title:Sem-Detect: Semantic Level Detection of AI Generated Peer-Reviews

View a PDF of the paper titled Sem-Detect: Semantic Level Detection of AI Generated Peer-Reviews, by Andr\'e V. Duarte and 4 other authors

View PDF HTML (experimental)

Abstract:How can we distinguish whether a peer review was written by a human or generated by an AI model? We argue that, in this setting, authorship should not be attributed solely from the textual features of a review, but also from the ideas, judgments, and claims it expresses. To this end, we propose Sem-Detect, an authorship detection method for peer reviews that operationalizes this principle by combining textual features with claim-level semantic analysis. Sem-Detect compares a target review against multiple AI-generated reviews of the same paper, leveraging the observation that different AI models tend to converge on similar points, while human reviewers introduce more unique and diverse ones. As a result, Sem-Detect is able to distinguish fully AI reviews from authentic human-written ones, including those that have been refined using an LLM but still reflect human judgment. Across a dataset of over 20,000 peer reviews from ICLR and NeurIPS conferences, Sem-Detect improves over the strongest baseline by 25.5% in [email protected]% FPR in the binary setting. Moreover, in the three-class scenario, we empirically show that LLM refinement preserves the semantic signals of human reviews, which remain distinct from the patterns exhibited by fully AI-generated text; as a result, fewer than 3.5% of LLM-refined human reviews are misclassified as AI-generated.

Subjects:

Computation and Language (cs.CL)

ACM classes: I.2

Cite as: arXiv:2605.21713 [cs.CL]

(or arXiv:2605.21713v1 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2605.21713

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: André Duarte [view email] [v1] Wed, 20 May 2026 20:19:16 UTC (911 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Sem-Detect: Semantic Level Detection of AI Generated Peer-Reviews, by Andr\'e V. Duarte and 4 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.CL

new | recent | 2026-05

Change to browse by:

cs

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)