AI-Generated Text Detection

Follow this topic Ask about this topic

Momentum

16 papers in the last four weeks, up 100% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 114

May 3, 2026cs.CL

Beyond Perplexity: Character Distribution Signatures and the MDTA Benchmark for AI Text Detection

Training-free AI text detection methods primarily rely on model log-probabilities, achieving strong performance through approaches like Binoculars and DNA-DetectLLM. However, these methods face a fundamental ceiling as models are optimized through RLHF to produce human-like probability distributions. We introduce an alternative detection signal based on character distribution signatures. We provide theoretical foundations showing that AI models, trained on massive domain-balanced corpora, approximate global character patterns while humans exhibit domain-specialized distributions, creating a "Wall of Separation" where human-AI divergence significantly exceeds AI-AI divergence. To enable systematic evaluation, we construct the Models-Domains-Temperatures-Adversarials (MDTA) benchmark comprising 642,274 prompt-aligned samples across 4 models, 5 domains, 3 temperature settings, and 3 adversarial strategies, substantially expanding the HC3 dataset with modern model responses, temperature variation, and adversarial augmentation. We introduce the Letter Distribution Score (LD-Score), demonstrating low correlation (r = 0.08-0.13) with perplexity methods. When integrated with DNA-DetectLLM, Binoculars and FastDetectGPT via a non-linear classifier, LD-Score yields consistent improvements in AUROC and F1, with particularly pronounced gains in specialized domains where vocabulary constraints amplify the detection signal. The MDTA dataset can be accessed at: https://huggingface.co/datasets/nsp909/MDTA.

Priyadarshan Narayanasamy, Swastik Agrawal, Klint Faber +1

Department of Computer Science, University of Maryland, College Park

AI-Generated Text Detection Robustness of Machine-Generated Text Detection

May 2, 2026cs.CL

LLM Output Detectability and Task Performance Can be Jointly Optimized

Detecting machine-generated text is essential for transparency and accountability when deploying large language models (LLMs). Among detection approaches, watermarking is a statistically reliable method by design -- it embeds detectable signals into LLM outputs by biasing their token distributions. However, it has been reported that watermarked LLMs often perform worse on downstream tasks. We propose PUPPET, a framework that fine-tunes an LLM via reinforcement learning to generate text that is both more detectable and better performing on downstream tasks. We use two reward functions: a detector that outputs a machine-class likelihood and an evaluator that measures a task-specific metric. Experiments on long-form QA, summarization, and essay writing show that LLMs trained with PUPPET achieve high detectability competitive with watermarking methods while outperforming them on downstream tasks. The analysis shows that this optimization can be performed efficiently with only a few thousand samples in 1--2 GPU hours. Moreover, these gains are consistent across out-of-domain tasks, different LLM families, and model sizes, and are even robust to paraphrasing attacks.

Koshiro Saito, Ryuto Koike, Masahiro Kaneko +1

Institute of Science Tokyo · MBZUAI · National Institute of Advanced Industrial Science and Technology +1

AI-Generated Text Detection LLM Watermarking

Apr 30, 2026cs.LG

StyleShield: Exposing the Fragility of AIGC Detectors through Continuous Controllable Style Transfer

AI-generated content (AIGC) detectors are increasingly deployed in high-stakes settings such as academic integrity screening, yet their reliability rests on a fundamental paradox: as language models are trained on human-written corpora, the statistical boundary between AI and human writing will inevitably dissolve as models improve. Commercial incentives have further distorted this landscape -- detection services and "de-AIification" tools often operate within the same supply chain, replacing evaluation of content quality with judgment of content origin. We present StyleShield, the first flow matching framework for conditional text style transfer, operating directly in continuous token embedding space via a DiT backbone with zero-initialized cross-attention adapters conditioned on frozen Qwen-7B representations. At inference, we adapt the SDEdit paradigm from image synthesis to text embeddings, with a single parameter gamma providing smooth continuous control over the evasion-preservation trade-off. On a multi-domain Chinese benchmark, StyleShield achieves 94.6% evasion against the training detector and >=99% against three unseen detectors, maintaining 0.928 semantic similarity. We further introduce RateAudit, a document-level scheduling algorithm that demonstrates detection-rate verdicts can be set to arbitrary values, directly questioning the reliability of score-based evaluation.

Guantian Zheng

Flow Matching AI-Generated Text Detection Robustness of Machine-Generated Text Detection Text Generation Adversarial Text Attacks

Apr 30, 2026cs.NI

DeGenTWeb: A First Look at LLM-dominant Websites

Many recent news reports have claimed that content generated by large language models (LLMs) is taking over the web. However, these claims are typically not based on a representative sample of the web and the methodology underlying them is often opaque. Moreover, when aiming to minimize the chances of falsely attributing human-authored content to LLMs, we find that detectors of LLM-generated text perform much worse than advertised. Consequently, we lack an understanding of the true prevalence and characteristics of LLM content on the web. We describe DeGenTWeb which systematically identifies LLM-dominant websites: sites whose content has been generated using LLMs with little human input. We show how to adapt detectors of LLM-generated text for use on web pages, and how to aggregate detection results from multiple pages on a site for accurate site-level categorization. Using DeGenTWeb, we find that LLM-dominant sites are highly prevalent both in data from Common Crawl and in Bing's search results, and that this share is growing over time. We also show that continuing to accurately identify such sites appears challenging given the capabilities of the latest LLMs.

Sichang Steven He, Calvin Ardi, Ramesh Govindan +1

University of Southern California · Unaliated

AI-Generated Text Detection

Apr 29, 2026cs.CL

DSIPA: Detecting LLM-Generated Texts via Sentiment-Invariant Patterns Divergence Analysis

The rapid advancement of large language models (LLMs) presents new security challenges, particularly in detecting machine-generated text used for misinformation, impersonation, and content forgery. Most existing detection approaches struggle with robustness against adversarial perturbation, paraphrasing attacks, and domain shifts, often requiring restrictive access to model parameters or large labeled datasets. To address this, we propose DSIPA, a novel training-free framework that detects LLM-generated content by quantifying sentiment distributional stability under controlled stylistic variation. It is based on the observation that LLMs typically exhibit more emotionally consistent outputs, while human-written texts display greater affective variation. Our framework operates in a zero-shot, black-box manner, leveraging two unsupervised metrics, sentiment distribution consistency and sentiment distribution preservation, to capture these intrinsic behavioral asymmetries without the need for parameter updates or probability access. Extensive experiments are conducted on state-of-the-art proprietary and open-source models, including GPT-5.2, Gemini-1.5-pro, Claude-3, and LLaMa-3.3. Evaluations on five domains, such as news articles, programming code, student essays, academic papers, and community comments, demonstrate that DSIPA improves F1 detection scores by up to 49.89% over baseline methods. The framework exhibits superior generalizability across domains and strong resilience to adversarial conditions, providing a robust and interpretable behavioral signal for secure content identification in the evolving LLM landscape.

Siyuan Li, Aodu Wulianghai, Guangyan Li +5

School of Computer Science, Shanghai Jiao Tong University, Shanghai, China · Shanghai Key Laboratory of Integrated Administration Technologies for Information Security, Shanghai, China · State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China

AI-Generated Text Detection LLM Security Robustness of Machine-Generated Text Detection

Apr 28, 2026cs.CL

Luminol-AIDetect: Fast Zero-shot Machine-Generated Text Detection based on Perplexity under Text Shuffling

Machine-generated text (MGT) detection requires identifying structurally invariant signals across generation models, rather than relying on model-specific fingerprints. In this respect, we hypothesize that while large language models excel at local semantic consistency, their autoregressive nature results in a specific kind of structural fragility compared to human writing. We propose Luminol-AIDetect, a novel, zero-shot statistical approach that exposes this fragility through coherence disruption. By applying a simple randomized text-shuffling procedure, we demonstrate that the resulting shift in perplexity serves as a principled, model-agnostic discriminant, as MGT displays a characteristic dispersion in perplexity-under-shuffling that differs markedly from the more stable structural variability of human-written text. Luminol-AIDetect leverages this distinction to inform its decision process, where a handful of perplexity-based scalar features are extracted from an input text and its shuffled version, then detection is performed via density estimation and ensemble-based prediction. Evaluated across 8 content domains, 11 adversarial attack types, and 18 languages, Luminol-AIDetect demonstrates state-of-the-art performance, with gains up to 17x lower FPR while being cheaper than prior methods.

Lucio La Cava, Andrea Tagarelli

DIMES Dept., University of Calabria v. P. Bucci 44Z, 87036 Rende, CS, Italy

AI-Generated Text Detection

Apr 28, 2026cs.CR

MGTEVAL: An Interactive Platform for Systemtic Evaluation of Machine-Generated Text Detectors

We present MGTEVAL, an extensible platform for systematic evaluation of Machine-Generated Text (MGT) detectors. Despite rapid progress in MGT detection, existing evaluations are often fragmented across datasets, preprocessing, attacks, and metrics, making results hard to compare and reproduce. MGTEVAL organizes the workflow into four components: Dataset Building, Dataset Attack, Detector Training, and Performance Evaluation. It supports constructing custom benchmarks by generating MGT with configurable LLMs, applying 12 text attacks to test sets, training detectors via a unified interface, and reporting effectiveness, robustness, and efficiency. The platform provides both command-line and Web-based interfaces for user-friendly experimentation without code rewriting.

Yuanfan Li, Qi Zhou, Chengzhengxu Li +5

Faculty of Electronic and Information Engineering, Xi’an Jiaotong University · Queen Mary University of London

AI-Generated Text Detection Language Model Generation Evaluation Language Model Robustness Robustness of Machine-Generated Text Detection

Apr 25, 2026cs.HC

Can Humans Detect AI? Mining Textual Signals of AI-Assisted Writing Under Varying Scrutiny Conditions

This study asks whether the threat of AI detection changes how people write with AI, and whether other people can tell the difference. In a two-phase controlled experiment, 21 participants wrote opinion pieces on remote work using an AI chatbot. Half were randomly warned that their submission would be scanned by an AI detection tool. The other half received no warning. Both groups had access to the same chatbot. In Phase 2, 251 independent judges evaluated 1,999 paired comparisons, each time choosing which document in the pair was written by a human. Judges were not told that both writers had access to AI. Across all evaluations, judges selected the warned writer's document as human 54.13% of the time versus 45.87% for the unwarned writer. A two-sided binomial test rejects chance guessing at p = 0.000243, and the result holds across both writing stances. Yet on every measurable text feature extracted, including AI overlap scores, lexical diversity, sentence structure, and pronoun usage, the two groups were indistinguishable. The judges are picking up on something that feature-based methods do not capture.

Daniel Tabach

Georgia Institute of Technology

AI-Generated Text Detection Human-AI Collaboration

Apr 23, 2026cs.LG

mcdok at SemEval-2026 Task 13: Finetuning LLMs for Detection of Machine-Generated Code

Multi-domain detection of the machine-generated code snippets in various programming languages is a challenging task. SemEval-2026 Task~13 copes with this challenge in various angles, as a binary detection problem as well as attribution of the source. Specifically, its subtasks also cover generator LLM family detection, as well as a hybrid code co-generated by humans and machines, or adversarially modified codes hiding its origin. Our submitted systems adjusted the existing mdok approach (focused on machine-generated text detection) to these specific kinds of problems by exploring various base models, more suitable for code understanding. The results indicate that the submitted systems are competitive in all three subtasks. However, the margins from the top-performing systems are significant, and thus further improvements are possible.

Adam Skurla, Dominik Macko, Jakub Simko

Faculty of Information Technology, Brno University of Technology, Brno, Czechia · Kempelen Institute of Intelligent Technologies, Bratislava, Slovakia

AI-Generated Text Detection LLM Fine-Tuning Authorship Attribution Classification

Apr 23, 2026cs.CL

Explainable Disentangled Representation Learning for Generalizable Authorship Attribution in the Era of Generative AI

Learning robust representations of authorial style is crucial for authorship attribution and AI-generated text detection. However, existing methods often struggle with content-style entanglement, where models learn spurious correlations between authors' writing styles and topics, leading to poor generalization across domains. To address this challenge, we propose Explainable Authorship Variational Autoencoder (EAVAE), a novel framework that explicitly disentangles style from content through architectural separation-by-design. EAVAE first pretrains style encoders using supervised contrastive learning on diverse authorship data, then finetunes with a Variational Autoencoder (VEA) architecture using separate encoders for style and content representations. Disentanglement is enforced through a novel discriminator that not only distinguishes whether pairs of style/content representations belong to the same or different authors/content sources, but also generates natural language explanation for their decision, simultaneously mitigating confounding information and enhancing interpretability. Extensive experiments demonstrate the effectiveness of EAVAE. On authorship attribution, we achieve state-of-the-art performance on various datasets, including Amazon Reviews, PAN21, and HRS. For AI-generated text detection, EAVAE excels in few-shot learning over the M4 dataset. Code and data repositories are available online\footnote{https://github.com/hieum98/avae} \footnote{https://huggingface.co/collections/Hieuman/document-level-authorship-datasets}.

Hieu Man, Van-Cuong Pham, Nghia Trung Ngo +2

University of Oregon, OR, USA · Adobe Research, CA, USA

Variational Autoencoders Disentangled Representation Learning Explainable Artificial Intelligence AI-Generated Text Detection Domain Generalization Authorship Attribution

Apr 23, 2026cs.CL

Zero-Shot Detection of LLM-Generated Text via Implicit Reward Model

Large language models (LLMs) have demonstrated remarkable capabilities across various tasks. However, their ability to generate human-like text has raised concerns about potential misuse. This underscores the need for reliable and effective methods to detect LLM-generated text. In this paper, we propose IRM, a novel zero-shot approach that leverages Implicit Reward Models for LLM-generated text detection. Such implicit reward models can be derived from publicly available instruction-tuned and base models. Previous reward-based method relies on preference construction and task-specific fine-tuning. In comparison, IRM requires neither preference collection nor additional training. We evaluate IRM on the DetectRL benchmark and demonstrate that IRM can achieve superior detection performance, outperforms existing zero-shot and supervised methods in LLM-generated text detection.

Runheng Liu, Heyan Huang, Xingchen Xiao +1

School of Computer Science and Technology, Beijing Institute of Technology

Zero-Shot Learning AI-Generated Text Detection

Apr 22, 2026cs.SE

Evaluating Assurance Cases as Text-Attributed Graphs for Structure and Provenance Analysis

An assurance case is a structured argument document that justifies claims about a system's requirements or properties, which are supported by evidence. In regulated domains, these are crucial for meeting compliance and safety requirements to industry standards. We propose a graph diagnostic framework for analysing the structure and provenance of assurance cases. We focus on two main tasks: (1) link prediction, to learn and identify connections between argument elements, and (2) graph classification, to differentiate between assurance cases created by a state-of-the-art large language model and those created by humans, aiming to detect bias. We compiled a publicly available dataset of assurance cases, represented as graphs with nodes and edges, supporting both link prediction and provenance analysis. Experiments show that graph neural networks (GNNs) achieve strong link prediction performance (ROC-AUC 0.760) on real assurance cases and generalise well across domains and semi-supervised settings. For provenance detection, GNNs effectively distinguish human-authored from LLM-generated cases (F1 0.94). We observed that LLM-generated assurance cases have different hierarchical linking patterns compared to human-authored cases. Furthermore, existing GNN explanation methods show only moderate faithfulness, revealing a gap between predicted reasoning and the true argument structure.

Fariz Ikhwantri, Dusica Marijan

Simula Research Laboratory Oslo, Norway

AI Assurance AI-Generated Text Detection Data Provenance Text-Attributed Graph Learning

Apr 21, 2026cs.AI

Reasoning-Aware AIGC Detection via Alignment and Reinforcement

The rapid advancement and widespread adoption of Large Language Models (LLMs) have elevated the need for reliable AI-generated content (AIGC) detection, which remains challenging as models evolve. We introduce AIGC-text-bank, a comprehensive multi-domain dataset with diverse LLM sources and authorship scenarios, and propose REVEAL, a detection framework that generates interpretable reasoning chains before classification. Our approach uses a two-stage training strategy: supervised fine-tuning to establish reasoning capabilities, followed by reinforcement learning to improve accuracy, improve logical consistency, and reduce hallucinations. Extensive experiments show that REVEAL achieves state-of-the-art performance across multiple benchmarks, offering a robust and transparent solution for AIGC detection. The project is open-source at https://aka.ms/reveal

Zhao Wang, Max Xiong, Jianxun Lian +1

Gaoling School of Artificial Intelligence, Renmin University of China · Duke University · Microsoft Research Asia

AI-Generated Text Detection

Apr 18, 2026cs.AI

Alignment Imprint: Zero-Shot AI-Generated Text Detection via Provable Preference Discrepancy

Detecting AI-generated text is an important but challenging problem. Existing likelihood-based detection methods are often sensitive to content complexity and may exhibit unstable performance. In this paper, our key insight is that modern Large Language Models (LLMs) undergo alignment (including fine-tuning and preference tuning), leaving a measurable distributional imprint. We theoretically derive this imprint by abstracting the alignment process as a sequence of constrained optimization steps, showing that the log-likelihood ratio can naturally decompose into implicit instructional biases and preference rewards. We refer to this quantity as the Alignment Imprint. Furthermore, to mitigate the instability in high-entropy regions, we introduce Log-likelihood Alignment Preference Discrepancy (LAPD), a standardized information-weighted statistic based on alignment imprint. We provide statistical guarantee that alignment-based statistics dominate Fast-DetectGPT in performance. We also theoretically show that LAPD strictly improves the unweighted alignment scores when the aligned and base models are close in distribution. Extensive experiments show that LAPD achieves an improvement 45.82% relative to the strongest existing baselines, yielding large and consistent gains across all settings.

Junxi Wu, Kailin Huang, Dongjian Hu +4

Nankai University · Tsinghua University · Wuhan University +3

LLM Alignment AI-Generated Text Detection

Apr 17, 2026cs.CL

Spotlights and Blindspots: Evaluating Machine-Generated Text Detection

With the rise of generative language models, machine-generated text detection has become a critical challenge. A wide variety of models is available, but inconsistent datasets, evaluation metrics, and assessment strategies obscure comparisons of model effectiveness. To address this, we evaluate 15 different detection models from six distinct systems, as well as seven trained models, across seven English-language textual test sets and three creative human-written datasets. We provide an empirical analysis of model performance, the influence of training and evaluation data, and the impact of key metrics. We find that no single system excels in all areas and nearly all are effective for certain tasks, and the representation of model performance is critically linked to dataset and metric choices. We find high variance in model ranks based on datasets and metrics, and overall poor performance on novel human-written texts in high-risk domains. Across datasets and metrics, we find that methodological choices that are often assumed or overlooked are essential for clearly and accurately reflecting model performance.

Kevin Stowe, Kailash Patil

Pindrop

AI-Generated Text Detection Language Model Generation Evaluation OOD Generalization Robustness of Machine-Generated Text Detection Generative AI Evaluation

Apr 16, 2026cs.CL

PeerPrism: Peer Evaluation Expertise vs Review-writing AI

Large Language Models (LLMs) are increasingly used in scientific peer review, assisting with drafting, rewriting, expansion, and refinement. However, existing peer-review LLM detection methods largely treat authorship as a binary problem-human vs. AI-without accounting for the hybrid nature of modern review workflows. In practice, evaluative ideas and surface realization may originate from different sources, creating a spectrum of human-AI collaboration. In this work, we introduce PeerPrism, a large-scale benchmark of 20,690 peer reviews explicitly designed to disentangle idea provenance from text provenance. We construct controlled generation regimes spanning fully human, fully synthetic, and multiple hybrid transformations. This design enables systematic evaluation of whether detectors identify the origin of the surface text or the origin of the evaluative reasoning. We benchmark state-of-the-art LLM text detection methods on PeerPrism. While several methods achieve high accuracy on the standard binary task (human vs. fully synthetic), their predictions diverge sharply under hybrid regimes. In particular, when ideas originate from humans but the surface text is AI-generated, detectors frequently disagree and produce contradictory classifications. Accompanied by stylometric and semantic analyses, our results show that current detection methods conflate surface realization with intellectual contribution. Overall, we demonstrate that LLM detection in peer review cannot be reduced to a binary attribution problem. Instead, authorship must be modeled as a multidimensional construct spanning semantic reasoning and stylistic realization. PeerPrism is the first benchmark evaluating human-AI collaboration in these settings. We release all code, data, prompts, and evaluation scripts to facilitate reproducible research at https://github.com/Reviewerly-Inc/PeerPrism.

Soroush Sadeghian, Alireza Daqiq, Radin Cheraghi +3

Reviewerly Toronto, Ontario, Canada · University of Toronto, Reviewerly Toronto, Ontario, Canada · UC Berkeley, Reviewerly Berkeley, California, United States

LLM Evaluation AI-Generated Text Detection Scholarly Peer Review Authorship Attribution

Apr 10, 2026cs.CL

Human vs. Machine Deception: Distinguishing AI-Generated and Human-Written Fake News Using Ensemble Learning

The rapid adoption of large language models has introduced a new class of AI-generated fake news that coexists with traditional human-written misinformation, raising important questions about how these two forms of deceptive content differ and how reliably they can be distinguished. This study examines linguistic, structural, and emotional differences between human-written and AI-generated fake news and evaluates machine learning and ensemble-based methods for distinguishing these content types. A document-level feature representation is constructed using sentence structure, lexical diversity, punctuation patterns, readability indices, and emotion-based features capturing affective dimensions such as fear, anger, joy, sadness, trust, and anticipation. Multiple classification models, including logistic regression, random forest, support vector machines, extreme gradient boosting, and a neural network, are applied alongside an ensemble framework that aggregates predictions across models. Model performance is assessed using accuracy and area under the receiver operating characteristic curve. The results show strong and consistent classification performance, with readability-based features emerging as the most informative predictors and AI-generated text exhibiting more uniform stylistic patterns. Ensemble learning provides modest but consistent improvements over individual models. These findings indicate that stylistic and structural properties of text provide a robust basis for distinguishing AI-generated misinformation from human-written fake news.

Samuel Jaeger, Calvin Ibenye, Aya Vera-Jimenez +1

School of Data Science and Analytics, Kennesaw State University, Kennesaw, GA · Department of Computer Science, Kennesaw State University, Kennesaw, GA · Department of Mathematics, Kennesaw State University, Kennesaw, GA

Fake News Detection AI-Generated Text Detection Text Classification

Mar 20, 2026cs.CL

Policies Permitting LLM Use for Polishing Peer Reviews Are Currently Not Enforceable

A number of scientific conferences and journals have recently enacted policies that prohibit LLM usage by peer reviewers, except for polishing, paraphrasing, and grammar correction of otherwise human-written reviews. But, are these policies enforceable? To answer this question, we assemble a dataset of peer reviews simulating multiple levels of human-AI collaboration, and evaluate five state-of-the-art detectors, including two commercial systems. Our analysis shows that all detectors misclassify a non-trivial fraction of LLM-polished reviews as AI-generated, thereby risking false accusations of academic misconduct. We further investigate whether peer-review-specific signals, including access to the paper manuscript and the constrained domain of scientific writing, can be leveraged to improve detection. While incorporating such signals yields measurable gains in some settings, we identify limitations in each approach and find that none meets the accuracy standards required for identifying AI use in peer reviews. Importantly, our results suggest that recent public estimates of AI use in peer reviews through the use of AI-text detectors should be interpreted with caution, as current detectors misclassify mixed reviews (collaborative human-AI outputs) as fully AI generated, potentially overstating the extent of policy violations.

Rounak Saha, Gurusha Juneja, Dayita Chaudhuri +3

♠Indian Institute of Science · ♢University of California, Santa Barbara · ♡Carnegie Mellon University

LLM Evaluation AI-Generated Text Detection Scholarly Peer Review

Mar 19, 2026cs.CL

The Truncation Blind Spot: How Decoding Strategies Systematically Exclude Human-Like Token Choices

Why does machine-generated text remain detectable? We investigate a mechanistic explanation at the decoding stage: standard strategies such as top-

k

and nucleus sampling restrict generation to high-probability tokens, while human writers routinely choose contextually appropriate words from deeper in the model's probability distribution. Truncation makes a measurable share of these choices unreachable; we call this the \emph{truncation blind spot}. Across five open models and three domains, 8--18% of human-selected tokens fall outside common truncation boundaries. Linguistic analysis further reveals disproportionate exclusion of content-word tokens. In a benchmark comprising 1.8 million machine generations, classifiers using only predictability and lexical diversity achieve mean AUC-ROC near 0.97, with substantial variation across decoding settings and strong transfer across generators. Probability-floor samplers substantially narrow the blind spot, demonstrating that the choice of truncation criterion matters for retaining human-used tokens. Together, these findings characterize a source of human--machine distributional mismatch and motivate decoding methods that preserve contextually appropriate low-probability choices while maintaining generation quality. Code and data are available at https://github.com/EstebanGarces/human_vs_machine.

Esteban Garces Arias, Nurzhan Sapargali, Christian Heumann +1

Department of Statistics, LMU Munich · Munich Center for Machine Learning (MCML)

AI-Generated Text Detection Language Model Decoding

Mar 16, 2026cs.CL

Interpretable Predictability-Based AI Text Detection: A Replication Study

This paper replicates and extends the system used in the AuTexTification shared task for authorship attribution of machine-generated texts. Exact replication was not possible because of differences in data splits, model availability, and implementation details, which we document as a case study in reproducibility. We tested newer multilingual language models (mDeBERTa-v3-base, Qwen, mGPT) and added 26 document-level stylometric features, using ablation, permutation importance, and SHAP analysis to assess feature influence. A single shared configuration was applied to both English and Spanish across Subtask 1 and Subtask 2. Averaged over three random seeds, the shared multilingual configuration performs comparably to or better than the language-specific baseline, with the clearest gains on model attribution (Subtask 2). The additional stylometric features yield small improvements, led by lexical diversity, but their contribution falls within seed variance once predictability-based probabilities are included, which remain the dominant signal. The study also shows that clear documentation is important for reliable replication and fair comparison of systems.

Adam Skurla, Dominik Macko, Jakub Simko

Faculty of Information Technology, Brno University of Technology, Brno, Czechia · Kempelen Institute of Intelligent Technologies, Bratislava, Slovakia

AI-Generated Text Detection Language Model Fingerprinting Authorship Attribution

Oct 8, 2025cs.LG

Black-Box Detection of LLM-Generated Text Using Generalized Jensen-Shannon Divergence

We study black-box detection of machine-generated text under practical constraints: the scoring model (proxy LM) may mismatch the unknown source model, and per-input contrastive generation is costly. We propose SurpMark, a reference-based detector that summarizes a passage by the dynamics of its token surprisals. SurpMark discretizes surprisals into interpretable states, estimates a state-transition matrix for the test text, and scores it via a generalized Jensen-Shannon (GJS) gap between the test transitions and two fixed references (human vs. machine) built once from existing corpora. Theoretically, we derive design guidance for how the discretization bins should scale with data and provide a principled justification for our test statistic. Empirically, across multiple datasets, source models, and scenarios, SurpMark consistently matches or surpasses baselines, demonstrating strong robustness across domains and generators; our experiments on hyperparameter sensitivity exhibit trends that our theoretical results help to explain.

Shuangyi Chen, Ashish Khisti

Department of Electrical and Computer Engineering, University of Toronto, Toronto, Canada.

AI-Generated Text Detection Language Model Robustness Robustness of Machine-Generated Text Detection

Sep 30, 2025cs.CL

VietBinoculars: A Zero-Shot Approach for Detecting Vietnamese LLM-Generated Text

The rapid proliferation of Large Language Models has intensified the challenge of distinguishing LLM-generated text from human writing in non-English languages. This study introduces VietBinoculars, a zero-shot detection framework coupling PhoGPT-4B observer and performer models with calibrated global decision thresholds. By utilizing specialized Vietnamese BPE tokenization, the method eliminates byte-level fragmentation and probability dilution common in massive multilingual backbones. Evaluated across multi-domain benchmarks, VietBinoculars achieves an area under the ROC curve exceeding 0.99. Under optimal Youden's J thresholds and greedy decoding, detection accuracy reaches at least 98.78%, while significantly outperforming baseline Binoculars, zero-shot detectors, and commercial tools on creative Capybara prompts. Even under a strict false positive rate constraint of 0.06%, the detector maintains F1-scores between 83.15% and 94.70%. Detection performance consistently improves with sequence length, stabilizing at optimal accuracy for passages containing 450 to 550 tokens. Extended stress testing across 48 distinct model-decoding configurations and three post-generation rewriting strategies delineates practical operational boundaries. VietBinoculars exhibits robust resilience against single-pass paraphrasing and human-style revisions, but experiences notable performance degradation under high-entropy sampling and iterative double paraphrasing.

Trieu Hai Nguyen, Sivaswamy Akilesh

Faculty of Information Technology, Nha Trang University, 02 Nguyen Dinh Chieu Street, North Nha Trang 57100, Vietnam · Faculty of Business Administration, Swiss School of Business and Management Geneva, 12 Avenue des Morgines, Geneva 1213, Switzerland

AI-Generated Text Detection Language Model Robustness Robustness of Machine-Generated Text Detection

Date pendingcs.CL

Limits of LLM Text Detectors in Education

Students increasingly use the assistance of large language models (LLMs) in their academic writing. While slight assistance (e.g., grammar and style correction, as well as feedback) is permitted under most institutional policies, it is usually forbidden to offload entire writing tasks to LLMs. Unfortunately, current approaches to LLM-generated text detection predominantly assume a binary distinction between human-written and LLM-generated text, ignoring the breadth of realistic human-AI collaboration practices and limiting the validity of detection systems for educational assessment. In this paper, we propose a contribution-aware evaluation framework for LLM-based detection systems in education. We introduce a scale of eight student contribution levels that model realistic writing scenarios ranging from fully human-written texts to LLM-assisted revisions to fully LLM-generated and adversarially humanized texts. Institutional policies regarding LLM use can then be translated to thresholds of acceptable LLM assistance on this scale. We further present Generative Essay Detection in Education (GEDE), a novel benchmark dataset comprising more than 900 human-written and over 12,500 generated essays across 886 tasks and all contribution levels. Using this benchmark, we conduct a systematic evaluation of four state-of-the-art zero-shot and supervised detection methods across policy boundaries, contribution levels, generative models, out-of-distribution data, and text length. We show that most detectors struggle to accurately classify texts at intermediate student contribution levels, in particular LLM-assisted revisions of human-written texts. Such errors pose a substantial risk of false accusations, indicating that current text detection systems are (still) unsuitable to reliably support the enforcement of institutional policies regarding LLM assistance in education.

Lukas Gehring, Benjamin Paa\ssen

Faculty of Technology, Bielefeld University

LLM Evaluation AI-Generated Text Detection Generative AI in Education

Date pendingcs.CL

Inverse Turing Bench: Evaluating Language Models as Judges of Human vs. AI Dialogue

As AI systems integrate into online spaces, differentiating them from humans in conversations is increasingly important. We present Inverse Turing Bench, a benchmark that evaluates LLMs and other models on their ability to differentiate humans and AI in multi-turn text. The benchmark provides a collection of paired dialogue transcripts, wherein one dialogue is between two humans and the other is between a human and an AI. The task is to correctly identify which dialogue is human-only vs. human-AI. We evaluated a preliminary set of models against this benchmark, and found that GPTZero, Claude Opus-4.6, and GPT-5.5 achieve the highest accuracy: 89.41%, 77.92%, and 75.94% respectively. Our results suggest that statistical approaches to detection have semantic blind spots, but semantic approaches are susceptible to persona-prompting. Our work speaks to the Inverse Turing Test and motivates human-AI differentiation as a critical capability for AI systems. Our live benchmark can be found at https://huggingface.co/spaces/roc-hci/Inverse-Turing-Bench-Leaderboard.

William Hager, Ishika Rathi, Masum Hasan +1

University of Rochester · Independent Researcher · Stony Brook University

LLM Evaluation AI-Generated Text Detection Human-AI Interaction Multi-Turn Dialogue Evaluation