mlsanityData to 7 Oct 2026

AdaDetectGPT: Adaptive Detection of LLM-Generated Text with Statistical Guarantees

arXiv 2510.01268 ↗First posted 29 Sep 2025cs.CL cs.AI cs.LGcited by 20

Not on the map. Why?

Abstract (arXiv)

We study the problem of determining whether a piece of text has been authored by a human or by a large language model (LLM). Existing state of the art logits-based detectors make use of statistics derived from the log-probability of the observed text evaluated using the distribution function of a given source LLM. However, relying solely on log probabilities can be sub-optimal. In response, we introduce AdaDetectGPT -- a novel classifier that adaptively learns a witness function from training data to enhance the performance of logits-based detectors. We provide statistical guarantees on its true positive rate, false positive rate, true negative rate and false negative rate. Extensive numerical studies show AdaDetectGPT nearly uniformly improves the state-of-the-art method in various combination of datasets and LLMs, and the improvement can reach up to 37%. A python implementation of our method is available at https://github.com/Mamba413/AdaDetectGPT.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). Builds on 63 of its 99 references that are in the map. First posted on arXiv 29 Sep 2025.

Builds on

63 of 99 references.

References · 63

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  2. 2024The Llama 3 Herd of Modelscited by 14,192
  3. 2025Qwen2.5-VL Technical Reportcited by 5,418
  4. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  5. 2024Qwen2.5 Technical Reportcited by 4,713
  6. 2024GPT-4o System Cardcited by 4,467
  7. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,115
  8. 2025Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilitiescited by 3,655
  9. 2023Mistral 7Bcited by 3,065
  10. 2015Character-level Convolutional Networks for Text Classificationcited by 2,293
  11. 2024Gemma 2: Improving Open Language Models at a Practical Sizecited by 1,928
  12. 2018Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarizationcited by 1,308
38 more
  1. 2018Hierarchical Neural Story Generationcited by 1,182
  2. 2023DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvaturecited by 705
  3. 2023A Watermark for Large Language Modelscited by 667
  4. 2024DeepSeek LLM: Scaling Open-Source Language Models with Longtermismcited by 621
  5. 2019Release Strategies and the Social Impacts of Language Modelscited by 505
  6. 2019GLTR: Statistical Detection and Visualization of Generated Textcited by 490
  7. 2023How Close is ChatGPT to Human Experts? Comparison Corpus, Evaluation, and Detectioncited by 472
  8. 2023Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defensecited by 401
  9. 2023Robust Distortion-free Watermarks for Language Modelscited by 279
  10. 2023Fast-DetectGPT: Efficient Zero-Shot Detection of Machine-Generated Text via Conditional Probability Curvaturecited by 278
  11. 2019Automatic Detection of Generated Text is Easiest when Humans are Fooledcited by 260
  12. 2023Provable Robust Watermarking for AI-Generated Textcited by 259
  13. 2024Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Textcited by 255
  14. 2023Undetectable Watermarks for Language Modelscited by 208
  15. 2023DetectLLM: Leveraging Log Rank Information for Zero-Shot Detection of Machine-Generated Textcited by 207
  16. 2023RADAR: Robust AI-Text Detection via Adversarial Learningcited by 187
  17. 2023GPT detectors are biased against non-native English writerscited by 175
  18. 2023Generative artificial intelligence enhances creativity but reduces the diversity of novel contentcited by 165
  19. 2023DNA-GPT: Divergent N-Gram Analysis for Training-Free Detection of GPT-Generated Textcited by 127
  20. 2023Intrinsic Dimension Estimation for Robust Detection of AI-Generated Textscited by 111
  21. 2023A Survey on LLM-Generated Text Detection: Necessity, Methods, and Future Directionscited by 101
  22. 2023Unbiased Watermark for Large Language Modelscited by 100
  23. 2023Ghostbuster: Detecting Text Ghostwritten by Large Language Modelscited by 90
  24. 2023ChatGPT or Human? Detect and Explain. Explaining Decisions of Machine Learning Model for Detecting Short ChatGPT-generated Textcited by 84
  25. 2023OUTFOX: LLM-Generated Essay Detection Through In-Context Learning with Adversarially Generated Examplescited by 80
  26. 2022Do Language Models Plagiarize?cited by 72
  27. 2023A Survey on Detection of LLMs-Generated Contentcited by 70
  28. 2020Statistical Inference of the Value Function for Reinforcement Learning in Infinite Horizon Settingscited by 65
  29. 2024Adaptive Text Watermark for Large Language Modelscited by 60
  30. 2023Multiscale Positive-Unlabeled Detection of AI-Generated Textscited by 59
  31. 2023Stylometric Detection of AI-Generated Text in Twitter Timelinescited by 57
  32. 2024A Statistical Framework of Watermarks for Large Language Models: Pivot, Detection Efficiency and Optimal Rulescited by 53
  33. 2024DeTeCtive: Detecting AI-generated Text via Multi-Level Contrastive Learningcited by 52
  34. 2024WaterMax: breaking the LLM watermark detectability-robustness-quality trade-offcited by 48
  35. 2023A Resilient and Accessible Distribution-Preserving Watermark for Large Language Modelscited by 47
  36. 2024Token-Specific Watermarking with Enhanced Detectability and Semantic Coherence for Large Language Modelscited by 30
  37. 2024Robust Detection of Watermarks for Large Language Models Under Human Editscited by 29
  38. 2023Differentiate ChatGPT-generated and Human-written Medical Textscited by 26

50 most cited of 63 All 63 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 18.

20 papers.

Sort:

By area:

  1. 2026Detecting LLM-Generated Text with Performance Guaranteescited by 8
  2. 2026Learn-to-Distance: Distance Learning for Detecting LLM-Generated Textcited by 8
  3. 2025Uncertainty Quantification for Large Language Model Reward Learning under Heterogeneous Human Feedbackcited by 7
  4. 2026Segmenting Human-LLM Co-authored Text via Change Point Detectioncited by 5
  5. 2025On the Detectability of LLM-Generated Text: What Exactly Is LLM-Generated Text?cited by 3
  6. 2026A Difference-in-Difference Approach to Detecting AI-Generated Imagescited by 2
  7. 2026Breaking the Generator Barrier: Disentangled Representation for Generalizable AI-Text Detectioncited by 1
  8. 2026Alignment Imprint: Zero-Shot AI-Generated Text Detection via Provable Preference Discrepancycited by 1
  9. 2026DetectZoo: A Unified Toolkit for AI-Generated Content Detection Across Text, Audio, and Image Modalitiescited by 1
  10. 2026Variation is the Key: A Variation-Based Framework for LLM-Generated Text Detectioncited by 0
  11. 2026Lightweight Stylistic Consistency Profiling: Robust Detection of LLM-Generated Textual Content for Multimedia Moderationcited by 0
  12. 2026Steer-to-Detect: Probing Hidden Representations for Detection of LLM-Generated Textscited by 0
8 more
  1. 2026Multi-Level Contextual Token Relation Modeling for Machine-Generated Text Detectioncited by 0
  2. 2026Hidden Human-Like Nature of Machine-Generated Texts: Theory and Detection Enhancementcited by 0
  3. 2026A Distribution-Free Framework for Rewrite-Based Human-text Detection via Knockoff Filteringcited by 0
  4. 2026Detecting LLM-Generated Tokens in Human--LLM Coauthored Textcited by 0
  5. 2026Efficient Online LLM Watermark Detection via Rao-Blackwellized E-Processescited by 0
  6. 2026DWT-Fusion: A Signal-Based Framework for Training-Free LLM-Generated Text Detectioncited by 0
  7. 2026Two Conformal Constructions for Adaptive Within-Document AI-Text Screeningcited by 0
  8. 2026LA-CPD: Local-Evidence-Aware Change-Point Detection for Human-LLM Authorship Segmentationcited by 0