mlsanityData to 14 Oct 2026

Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Text

arXiv 2401.12070 ↗First posted 22 Jan 2024cs.CL cs.AI cs.LGcited by 263

Not on the map. Why?

Abstract (arXiv)

Detecting text generated by modern large language models is thought to be hard, as both LLMs and humans can exhibit a wide range of complex behaviors. However, we find that a score based on contrasting two closely related language models is highly accurate at separating human-generated and machine-generated text. Based on this mechanism, we propose a novel LLM detector that only requires simple calculations using a pair of pre-trained LLMs. The method, called Binoculars, achieves state-of-the-art accuracy without any training data. It is capable of spotting machine text from a range of modern LLMs without any model-specific modifications. We comprehensively evaluate Binoculars on a number of text sources and in varied situations. Over a wide range of document types, Binoculars detects over 90% of generated samples from ChatGPT (and other LLMs) at a false positive rate of 0.01%, despite not being trained on any ChatGPT data.

Key facts. Cited by 263 papers in the map (data through 14 Oct 2026). Builds on 36 of its 54 references that are in the map. First posted on arXiv 22 Jan 2024.

Builds on

36 of 54 references.

References · 36

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  3. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  4. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  5. 2022Fast Inference from Transformers via Speculative Decodingcited by 1,653
  6. 2015Teaching Machines to Read and Comprehendcited by 1,049
  7. 2023Accelerating Large Language Model Decoding with Speculative Samplingcited by 1,006
  8. 2023DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvaturecited by 726
  9. 2023A Watermark for Large Language Modelscited by 725
  10. 2022Contrastive Decoding: Open-ended Text Generation as Optimizationcited by 609
  11. 2019Defending Against Neural Fake Newscited by 559
  12. 2019Release Strategies and the Social Impacts of Language Modelscited by 513
24 more
  1. 2019GLTR: Statistical Detection and Visualization of Generated Textcited by 496
  2. 2023How Close is ChatGPT to Human Experts? Comparison Corpus, Evaluation, and Detectioncited by 481
  3. 2023Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defensecited by 429
  4. 2023Can AI-Generated Text be Reliably Detected?cited by 386
  5. 2023Fast-DetectGPT: Efficient Zero-Shot Detection of Machine-Generated Text via Conditional Probability Curvaturecited by 287
  6. 2023DetectLLM: Leveraging Log Rank Information for Zero-Shot Detection of Machine-Generated Textcited by 210
  7. 2023RADAR: Robust AI-Text Detection via Adversarial Learningcited by 190
  8. 2023GPT detectors are biased against non-native English writerscited by 178
  9. 2023DNA-GPT: Divergent N-Gram Analysis for Training-Free Detection of GPT-Generated Textcited by 129
  10. 2023The Science of Detecting LLM-Generated Textscited by 128
  11. 2023M4: Multi-generator, Multi-domain, and Multi-lingual Black-Box Machine-Generated Text Detectioncited by 121
  12. 2023Intrinsic Dimension Estimation for Robust Detection of AI-Generated Textscited by 112
  13. 2023Ghostbuster: Detecting Text Ghostwritten by Large Language Modelscited by 91
  14. 2023On the Possibilities of AI-Generated Text Detectioncited by 88
  15. 2022Machine Generated Text: A Comprehensive Survey of Threat Models and Detection Methodscited by 79
  16. 2023Multiscale Positive-Unlabeled Detection of AI-Generated Textscited by 61
  17. 2020Attacking Neural Text Detectorscited by 39
  18. 2023HowkGPT: Investigating the Detection of ChatGPT-generated University Student Homework through Context-Aware Perplexity Analysiscited by 30
  19. 2023Towards Possibilities & Impossibilities of AI-generated Text Detection: A Surveycited by 28
  20. 2023G3Detector: General GPT-Generated Text Detectorcited by 17
  21. 2020Limits of Detecting Text Generated by Large-Scale Language Modelscited by 15
  22. 2022Fooling MOSS Detection with Pretrained Language Modelscited by 12
  23. 2023Detecting ChatGPT: A Survey of the State of Detecting ChatGPT-Generated Textcited by 10
  24. 2023A Statistical Turing Test for Generative Modelscited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 42; 2025: 91; 2026: 130.

263 papers.

Sort:

By area:

  1. 2024LLM Evaluators Recognize and Favor Their Own Generationscited by 686
  2. 2024RAID: A Shared Benchmark for Robust Evaluation of Machine-Generated Text Detectorscited by 163
  3. 2025DeepScientist: Advancing Frontier-Pushing Scientific Findings Progressivelycited by 63
  4. 2024WaterMax: breaking the LLM watermark detectability-robustness-quality trade-offcited by 54
  5. 2024SoK: Watermarking for AI-Generated Contentcited by 51
  6. 2024Zero-Shot Detection of AI-Generated Imagescited by 50
  7. 2024M4GT-Bench: Evaluation Benchmark for Black-Box Machine-Generated Text Detectioncited by 43
  8. 2025People who frequently use ChatGPT for writing tasks are accurate and robust detectors of AI-generated textcited by 40
  9. 2024DetectRL: Benchmarking LLM-Generated Text Detection in Real-World Scenarioscited by 38
  10. 2024Training-free LLM-generated Text Detection by Mining Token Probability Sequencescited by 35
  11. 2024SemEval-2024 Task 8: Multidomain, Multimodel and Multilingual Machine-Generated Text Detectioncited by 30
  12. 2024Beemo: Benchmark of Expert-edited Machine-generated Outputscited by 27
38 more
  1. 2025EditLens: Quantifying the Extent of AI Editing in Textcited by 26
  2. 2025RepreGuard: Detecting LLM-Generated Text by Revealing Hidden Representation Patternscited by 24
  3. 2024Detecting AI-Generated Text: Factors Influencing Detectability with Current Methodscited by 23
  4. 2024The Rise of AI-Generated Content in Wikipediacited by 22
  5. 2025Is Your Paper Being Reviewed by an LLM? Benchmarking AI Text Detection in Peer Reviewcited by 21
  6. 2025AdaDetectGPT: Adaptive Detection of LLM-Generated Text with Statistical Guaranteescited by 21
  7. 2024Evaluation of LLM Vulnerabilities to Being Misused for Personalized Disinformation Generationcited by 20
  8. 2025DAMAGE: Detecting Adversarially Modified AI Generated Textcited by 20
  9. 2025Almost AI, Almost Human: The Challenge of Detecting AI-Polished Writingcited by 19
  10. 2024Are AI-Generated Text Detectors Robust to Adversarial Perturbations?cited by 16
  11. 2025Cost-Aware Contrastive Routing for LLMscited by 16
  12. 2024Exploring the Limitations of Detecting Machine-Generated Textcited by 15
  13. 2024Detecting Machine-Generated Texts: Not Just "AI vs Humans" and Explainability is Complicatedcited by 15
  14. 2025Human-LLM Coevolution: Evidence from Academic Writingcited by 15
  15. 2024MultiSocial: Multilingual Benchmark of Machine-Generated Text Detection of Social-Media Textscited by 14
  16. 2024Glimpse: Enabling White-Box Methods to Use Proprietary Models for Zero-Shot LLM-Generated Text Detectioncited by 14
  17. 2025Machine-generated text detection prevents language model collapsecited by 14
  18. 2024EAGLE: A Domain Generalization Framework for AI-generated Text Detectioncited by 13
  19. 2024DALD: Improving Logits-based Detector without Logits from Black-box LLMscited by 13
  20. 2024SilverSpeak: Evading AI-Generated Text Detectors using Homoglyphscited by 13
  21. 2025GenAI Content Detection Task 1: English and Multilingual Machine-Generated Text Detection: AI vs. Humancited by 13
  22. 2024AI "News" Content Farms Are Easy to Make and Hard to Detect: A Case Study in Italiancited by 12
  23. 2025DETree: DEtecting Human-AI Collaborative Texts via Tree-Structured Hierarchical Representation Learningcited by 12
  24. 2024Online Detection of LLM-Generated Texts via Sequential Hypothesis Testing by Bettingcited by 11
  25. 2025AI Safety Should Prioritize the Future of Workcited by 11
  26. 2025DNA-DetectLLM: Unveiling AI-Generated Text via a DNA-Inspired Mutation-Repair Paradigmcited by 11
  27. 2025Blackbox Model Provenance via Palimpsestic Membership Inferencecited by 11
  28. 2026GPTZero: Robust Detection of LLM-Generated Textscited by 11
  29. 2024Are AI Detectors Good Enough? A Survey on Quality of Datasets With Machine-Generated Textscited by 10
  30. 2024On the Generalization and Adaptation Ability of Machine-Generated Text Detectors in Academic Writingcited by 10
  31. 2025Reliably Bounding False Positives: A Zero-Shot Machine-Generated Text Detection Framework via Multiscaled Conformal Predictioncited by 10
  32. 2025Benchmarking the Detection of LLMs-Generated Modern Chinese Poetrycited by 10
  33. 2026Detecting LLM-Generated Text with Performance Guaranteescited by 10
  34. 2025Stress-testing Machine Generated Text Detection: Shifting Language Models Writing Style to Fool Detectorscited by 9
  35. 2025DivScore: Zero-Shot Detection of LLM-Generated Text in Specialized Domainscited by 9
  36. 2025Enhancing LLM Watermark Resilience Against Both Scrubbing and Spoofing Attackscited by 9
  37. 2025DetectAnyLLM: Towards Generalizable and Robust Detection of Machine-Generated Text Across Domains and Modelscited by 9
  38. 2026StoryScope: Investigating idiosyncrasies in AI fictioncited by 9

50 most cited of 263 All 263 (JSON)