mlsanityData to 7 Oct 2026

On the Possibilities of AI-Generated Text Detection

arXiv 2304.04736 ↗First posted 10 Apr 2023cs.CL cs.AI cs.LGcited by 88

Not on the map. Why?

Cited by 23 in LLM safety and security, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Our work addresses the critical issue of distinguishing text generated by Large Language Models (LLMs) from human-produced text, a task essential for numerous applications. Despite ongoing debate about the feasibility of such differentiation, we present evidence supporting its consistent achievability, except when human and machine text distributions are indistinguishable across their entire support. Drawing from information theory, we argue that as machine-generated text approximates human-like quality, the sample size needed for detection increases. We establish precise sample complexity bounds for detecting AI-generated text, laying groundwork for future research aimed at developing advanced, multi-sample detectors. Our empirical evaluations across multiple datasets (Xsum, Squad, IMDb, and Kaggle FakeNews) confirm the viability of enhanced detection methods. We test various state-of-the-art text generators, including GPT-2, GPT-3.5-Turbo, Llama, Llama-2-13B-Chat-HF, and Llama-2-70B-Chat-HF, against detectors, including oBERTa-Large/Base-Detector, GPTZero. Our findings align with OpenAI's empirical data related to sequence length, marking the first theoretical substantiation for these observations.

Key facts. Cited by 88 papers in the map (data through 7 Oct 2026). Builds on 22 of its 53 references that are in the map. First posted on arXiv 10 Apr 2023.

Builds on

22 of 53 references.

References · 22

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,115
  4. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  5. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,302
  6. 2018Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarizationcited by 1,308
  7. 2018Self-Attentive Sequential Recommendationcited by 1,169
  8. 2023DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvaturecited by 705
  9. 2023A Watermark for Large Language Modelscited by 667
  10. 2019Release Strategies and the Social Impacts of Language Modelscited by 505
  11. 2019GLTR: Statistical Detection and Visualization of Generated Textcited by 490
  12. 2023Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defensecited by 401
10 more
  1. 2015A Neural Attention Model for Abstractive Sentence Summarizationcited by 394
  2. 2023Can AI-Generated Text be Reliably Detected?cited by 372
  3. 2015Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Modelscited by 207
  4. 2023GPT detectors are biased against non-native English writerscited by 175
  5. 2022Modern Question Answering Datasets and Benchmarks: A Surveycited by 23
  6. 2021Question Answering Survey: Directions, Challenges, Datasets, Evaluation Matricescited by 17
  7. 2022Ask Me What You Need: Product Retrieval using Knowledge from GPT-3cited by 8
  8. 2022Rank-LIME: Local Model-Agnostic Feature Attribution for Learning to Rankcited by 7
  9. 2023Topics as Entity Clusters: Entity-based Topics from Large Language Models and Graph Neural Networkscited by 3
  10. 2022Cross-Lingual Phrase Retrievalcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 34; 2024: 35; 2025: 12; 2026: 7.

88 papers.

Sort:

By area:

  1. 2024Scaling Synthetic Data Creation with 1,000,000,000 Personascited by 397
  2. 2023Provable Robust Watermarking for AI-Generated Textcited by 259
  3. 2024Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Textcited by 255
  4. 2023Membership Inference Attacks against Language Models via Neighbourhood Comparisoncited by 249
  5. 2023Undetectable Watermarks for Language Modelscited by 208
  6. 2023RADAR: Robust AI-Text Detection via Adversarial Learningcited by 187
  7. 2023Can LLM-Generated Misinformation Be Detected?cited by 173
  8. 2023On the Reliability of Watermarks for Large Language Modelscited by 170
  9. 2024Monitoring AI-Modified Content at Scale: A Case Study on the Impact of ChatGPT on AI Conference Peer Reviewscited by 160
  10. 2023DNA-GPT: Divergent N-Gram Analysis for Training-Free Detection of GPT-Generated Textcited by 127
  11. 2023On the Risk of Misinformation Pollution with Large Language Modelscited by 124
  12. 2024Mapping the Increasing Use of LLMs in Scientific Paperscited by 112
38 more
  1. 2023Ghostbuster: Detecting Text Ghostwritten by Large Language Modelscited by 90
  2. 2023Testing of Detection Tools for AI-Generated Textcited by 86
  3. 2023Watermarks in the Sand: Impossibility of Strong Watermarking for Generative Modelscited by 77
  4. 2024Detecting Multimedia Generated by Large AI Models: A Surveycited by 73
  5. 2023A Survey on Detection of LLMs-Generated Contentcited by 70
  6. 2023Publicly-Detectable Watermarking for Language Modelscited by 69
  7. 2023Mark My Words: Analyzing and Evaluating Language Model Watermarkscited by 62
  8. 2023Red Teaming Language Model Detectors with Language Modelscited by 55
  9. 2023An Unforgeable Publicly Verifiable Watermark for Large Language Modelscited by 54
  10. 2023Fighting Fire with Fire: The Dual Role of LLMs in Crafting and Detecting Elusive Disinformationcited by 51
  11. 2024Raidar: geneRative AI Detection viA Rewritingcited by 51
  12. 2023A Resilient and Accessible Distribution-Preserving Watermark for Large Language Modelscited by 47
  13. 2023LLMDet: A Third Party Large Language Models Generated Text Detection Toolcited by 44
  14. 2023Origin Tracing and Detecting of LLMscited by 39
  15. 2023GPT-who: An Information Density-based Machine-Generated Text Detectorcited by 38
  16. 2023Anatomy of an AI-powered malicious social botnetcited by 35
  17. 2024TRAP: Targeted Random Adversarial Prompt Honeypot for Black-Box Identificationcited by 33
  18. 2024Training-free LLM-generated Text Detection by Mining Token Probability Sequencescited by 33
  19. 2024GumbelSoft: Diversified Language Model Watermarking via the GumbelMax-trickcited by 31
  20. 2023HowkGPT: Investigating the Detection of ChatGPT-generated University Student Homework through Context-Aware Perplexity Analysiscited by 30
  21. 2023Towards Possibilities & Impossibilities of AI-generated Text Detection: A Surveycited by 28
  22. 2023From Text to Source: Results in Detecting Large Language Model-Generated Contentcited by 25
  23. 2024Stumbling Blocks: Stress Testing the Robustness of Machine-Generated Text Detectors Under Attackscited by 25
  24. 2023WatME: Towards Lossless Watermarking Through Lexical Redundancycited by 22
  25. 2024Double-I Watermark: Protecting Model Copyright for LLM Fine-tuningcited by 18
  26. 2024Spotting AI's Touch: Identifying LLM-Paraphrased Spans in Textcited by 16
  27. 2024Beyond Binary: Towards Fine-Grained LLM-Generated Text Detection via Role Recognition and Involvement Measurementcited by 16
  28. 2023Game of Tones: Faculty detection of GPT-4 generated content in university assessmentscited by 15
  29. 2023Counter Turing Test CT^2: AI-Generated Text Detection is Not as Easy as You May Think -- Introducing AI Detectability Indexcited by 14
  30. 2024Decoding the AI Pen: Techniques and Challenges in Detecting AI-Generated Textcited by 14
  31. 2025Feature-Level Insights into Artificial Text Detection with Sparse Autoencoderscited by 14
  32. 2024DALD: Improving Logits-based Detector without Logits from Black-box LLMscited by 12
  33. 2024AI "News" Content Farms Are Easy to Make and Hard to Detect: A Case Study in Italiancited by 12
  34. 2024Excuse me, sir? Your language model is leaking (information)cited by 11
  35. 2024From Deception to Detection: The Dual Roles of Large Language Models in Fake Newscited by 11
  36. 2023Distinguishing Human Generated Text From ChatGPT Generated Text Using Machine Learningcited by 10
  37. 2024Hidding the Ghostwriters: An Adversarial Evaluation of AI-Generated Student Essay Detectioncited by 10
  38. 2024LLM-Detector: Improving AI-Generated Chinese Text Detection with Open-Source LLM Instruction Tuningcited by 10

50 most cited of 88 All 88 (JSON)