Do AI text detectors actually work?

Numbers match the citations in the article. A working link isn't proof that a page supports a claim; check the quoted passage and date.

1. 1

   GPT detectors are biased against non-native English writers

   Patterns (Liang et al.)Published Jul 1, 2023Checked Sep 30, 2026

   “Seven widely used GPT detectors misclassified over half of TOEFL essays written by non-native English speakers as AI-generated (an average false-positive rate of 61%), while classifying essays by US eighth-graders almost perfectly. Simple prompting strategies, such as asking a model to use more literary language, sharply reduced detection of AI-generated text. The authors caution against using detectors in evaluative or educational settings.”

2. 2

   Testing of detection tools for AI-generated text

   International Journal for Educational Integrity (Weber-Wulff et al.)Published Dec 24, 2023Checked Sep 30, 2026

   “Specifically, the study seeks to answer research questions about whether existing detection tools can reliably differentiate between human-written text and ChatGPT-generated text, and whether machine translation and content obfuscation techniques affect the detection of AI-generated text. The research covers 12 publicly available tools and two commercial systems (Turnitin and PlagiarismCheck) that are widely used in the academic setting. The researchers conclude that the available detection tools are neither accurate nor reliable and have a main bias towards classifying the output as human-written rather than detecting AI-generated text. Furthermore, content obfuscation techniques significantly worsen the performance of tools. The study makes several significant contributions. First, it summarises up-to-date similar scientific and non-scientific efforts in the field. Second, it presents the result of one of the most comprehensive tests conducted so far, based on a rigorous research methodology, an original document set, and a broad coverage of tools. Third, it discusses the implications and drawbacks of using detection tools for AI-generated text in academic settings.”

3. 3

   How Sensitive Are the Free AI-detector Tools in Detecting AI-generated Texts? A Comparison of Popular AI-detector Tools

   Indian Journal of Psychological Medicine (Kar et al.)Published May 11, 2024Checked Oct 4, 2026

   “10 AI-detector tools were tested on their ability to detect AI-generated text. The sensitivity ranged from 0% to 100%. 5 out of 10 tools detected AI-generated content with 100% accuracy. For paraphrased texts, Sapling and Undetectable AI detected all three software-generated contents with 100% accuracy. Meanwhile, Copyleaks, QuillBot , and Wordtune identified content generated by two software programs with 100% accuracy. The integration of AI technology in academic writing is becoming more prevalent. Nonetheless, relying solely on AI-generated content can diminish the author’s credibility, leading most academic journals to suggest limiting its use. AI-content-detection software programs have been developed to detect AI-generated or AI-assisted texts. Currently, some of the platforms are equally sensitive.”

4. 4

   The Effectiveness of Software Designed to Detect AI-Generated Writing: A Comparison of 16 AI Text Detectors

   Open Information Science (Walters)Published Jan 1, 2023Checked Oct 4, 2026

   “This study evaluates the accuracy of 16 publicly available AI text detectors in discriminating between AI-generated and human-generated writing. The evaluated documents include 42 undergraduate essays generated by ChatGPT-3.5, 42 generated by ChatGPT-4, and 42 written by students in a first-year composition course without the use of AI. Each detector’s performance was assessed with regard to its overall accuracy, its accuracy with each type of document, its decisiveness (the relative number of uncertain responses), the number of false positives (human-generated papers designated as AI by the detector), and the number of false negatives (AI-generated papers designated as human). Three detectors – Copyleaks, TurnItIn, and Originality.ai – have high accuracy with all three sets of documents. Although most of the other 13 detectors can distinguish between GPT-3.5 papers and human-generated papers with reasonably high accuracy, they are generally ineffective at distinguishing between GPT-4 papers and those written by undergraduate students. Overall, the detectors that require registration and payment are only slightly more accurate than the others.”

5. 5

   Accuracy and Reliability of AI-Generated Text Detection Tools: A Literature Review

   American Journal of IR 4 0 and Beyond (Gotoman et al.)Published Feb 18, 2025Checked Oct 4, 2026

   “This study used a literature review wherein pertinent studies were gathered and selected to discover potential implications. Research objectives were defined to assess the accuracy and reliability of the AI text detectors and identify which AI detectors were evaluated. Three online databases were used to search for relevant literature, of which 34 articles were finalized. Results show that despite most detectors attaining accuracy above 50%, they are unreliable. Paid tools generally perform better than free ones, but there are concerns about bias against non-native English speakers. These tools also struggle with sophisticated AI content and tricks like paraphrasing, so using them carefully and relying on human judgment is important to avoid unfairly discrediting someone’s work. AI-generated text detection technology still has a lot of room for improvement. Users should not rely completely on these tools but rather cooperate with those tools to better find the true writer of a text. Hence, authorities who use these AI detectors should only partially trust these tools, for they are imperfect and can still make mistakes in their judgment.”

6. 6

   Enhancing the Robustness of AI-Generated Text Detectors: A Survey

   Mathematics (Liu et al.)Published Jun 30, 2025Checked Oct 4, 2026

   “This survey provides a systematic overview of existing research on enhancing the robustness of AIGT detectors. We categorize the focus of related literature into three key areas: text perturbation robustness, out-of-distribution (OOD) robustness, and AI–human hybrid text (AHT) detection robustness. For each area, we thoroughly summarize and analyze the corresponding robustness enhancement methods and additionally incorporate some approaches from other fields as a supplement. We also methodically organize relevant benchmark datasets, robustness evaluation methods, and metrics used to assess detectors’ performance. Then, through experiments, we evaluate the robustness of several commonly used detectors. Experiments show that text perturbations, OOD text, and AHT all affect the performance of these detectors, revealing that there remains significant room for improvement in their robustness. Finally, we suggest promising future directions based on the current issues faced by AIGT detectors and the detection requirements in real-world scenarios. To the best of our knowledge, this is the first review focused specifically on the robustness of AIGT detection.”