mlsanityData to 14 Oct 2026

AI model GPT-3 (dis)informs us better than humans

arXiv 2301.11924 ↗First posted 23 Jan 2023cs.CY cs.AI cs.HCcited by 78

Not on the map. Why?

Abstract (arXiv)

Artificial intelligence is changing the way we create and evaluate information, and this is happening during an infodemic, which has been having dramatic effects on global health. In this paper we evaluate whether recruited individuals can distinguish disinformation from accurate information, structured in the form of tweets, and determine whether a tweet is organic or synthetic, i.e., whether it has been written by a Twitter user or by the AI model GPT-3. Our results show that GPT-3 is a double-edge sword, which, in comparison with humans, can produce accurate information that is easier to understand, but can also produce more compelling disinformation. We also show that humans cannot distinguish tweets generated by GPT-3 from tweets written by human users. Starting from our results, we reflect on the dangers of AI for disinformation, and on how we can improve information campaigns to benefit global health.

Key facts. Cited by 78 papers in the map (data through 14 Oct 2026). Builds on 4 of its 40 references that are in the map. First posted on arXiv 23 Jan 2023.

Builds on

4 of 40 references.

References · 4

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2021All That's 'Human' Is Not Gold: Evaluating Human Evaluation of Generated Textcited by 287
  3. 2021Detecting Hate Speech with GPT-3cited by 56
  4. 2021Tortured phrases: A dubious writing style emerging in science. Evidence of critical issues affecting established journalscited by 17

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 19; 2024: 24; 2025: 16; 2026: 19.

78 papers.

Sort:

By area:

  1. 2024Knowledge Conflicts for LLMs: A Surveycited by 283
  2. 2023Can LLM-Generated Misinformation Be Detected?cited by 177
  3. 2024RAID: A Shared Benchmark for Robust Evaluation of Machine-Generated Text Detectorscited by 163
  4. 2023Generative AIcited by 120
  5. 2023The Earth is Flat because...: Investigating LLMs' Belief towards Misinformation via Persuasive Conversationcited by 109
  6. 2023Language Model Behavior: A Comprehensive Surveycited by 92
  7. 2023Use of LLMs for Illicit Purposes: Threats, Prevention Measures, and Vulnerabilitiescited by 82
  8. 2025Large language models for automated scholarly paper review: A surveycited by 61
  9. 2024Large Language Model Safety: A Holistic Surveycited by 59
  10. 2023Generative Pre-trained Transformer: A Comprehensive Review on Enabling Technologies, Potential Applications, Emerging Challenges, and Future Directionscited by 55
  11. 2024Autonomous LLM-driven research from data to human-verifiable research paperscited by 53
  12. 2023Fighting Fire with Fire: The Dual Role of LLMs in Crafting and Detecting Elusive Disinformationcited by 51
38 more
  1. 2024AI-Driven Review Systems: Evaluating LLMs in Scalable and Bias-Aware Academic Reviewscited by 44
  2. 2023Disinformation Detection: An Evolving Challenge in the Age of LLMscited by 41
  3. 2023Neural Retrievers are Biased Towards LLM-Generated Contentcited by 38
  4. 2023Anatomy of an AI-powered malicious social botnetcited by 36
  5. 2024Persuasion with Large Language Models: A Survey of Empirical Evidence, Study Methodologies, and Ethical Implicationscited by 32
  6. 2023Overview of AuTexTification at IberLEF 2023: Detection and Attribution of Machine-Generated Text in Multiple Domainscited by 31
  7. 2024Scaling Trends for Data Poisoning in LLMscited by 30
  8. 2023Exploiting Novel GPT-4 APIscited by 28
  9. 2023Disentangling Perceptions of Offensiveness: Cultural and Moral Correlatescited by 26
  10. 2024Detecting AI-Generated Text: Factors Influencing Detectability with Current Methodscited by 23
  11. 2023Fact-checking information from large language models can decrease headline discernmentcited by 22
  12. 2024A Survey of AI-generated Text Forensic Systems: Detection, Attribution, and Characterizationcited by 19
  13. 2025LLM-Generated Fake News Induces Truth Decay in News Ecosystem: A Case Study on Neural News Recommendationcited by 19
  14. 2024When LLMs Play the Telephone Game: Cultural Attractors as Conceptual Tools to Evaluate LLMs in Multi-turn Settingscited by 17
  15. 2024Lies, Damned Lies, and Distributional Language Statistics: Persuasion and Deception with Large Language Modelscited by 15
  16. 2023Adapting Fake News Detection to the Era of Large Language Modelscited by 14
  17. 2024Large language models can consistently generate high-quality content for election disinformation operationscited by 14
  18. 2023Invisible Relevance Bias: Text-Image Retrieval Models Prefer AI-Generated Imagescited by 13
  19. 2025Labeling Messages as AI-Generated Does Not Reduce Their Persuasive Effectscited by 13
  20. 2024Fakes of Varying Shades: How Warning Affects Human Perception and Engagement Regarding LLM Hallucinationscited by 12
  21. 2024MetaSumPerceiver: Multimodal Multi-Document Evidence Summarization for Fact-Checkingcited by 10
  22. 2024Fake Artificial Intelligence Generated Contents (FAIGC): A Survey of Theories, Detection Methods, and Opportunitiescited by 8
  23. 2025GenAI Content Detection Task 3: Cross-Domain Machine-Generated Text Detection Challengecited by 7
  24. 2023In Generative AI we Trust: Can Chatbots Effectively Verify Political Information?cited by 6
  25. 2025Concept-Level Explainability for Auditing & Steering LLM Responsescited by 6
  26. 2025Linguistic and Embedding-Based Profiling of Texts generated by Humans and Large Language Modelscited by 6
  27. 2026JailNewsBench: Multi-Lingual and Regional Benchmark for Fake News Generation under Jailbreak Attackscited by 6
  28. 2024I Am Not Them: Fluid Identities and Persistent Out-group Bias in Large Language Modelscited by 5
  29. 2024Catching Chameleons: Detecting Evolving Disinformation Generated using Large Language Modelscited by 5
  30. 2024How will advanced AI systems impact democracy?cited by 5
  31. 2025Echoes of Power: Investigating Geopolitical Bias in US and China Large Language Modelscited by 5
  32. 2025Sword and Shield: Uses and Strategies of LLMs in Navigating Disinformationcited by 4
  33. 2024Lying Blindly: Bypassing ChatGPT's Safeguards to Generate Hard-to-Detect Disinformation Claimscited by 3
  34. 2025Increasing happiness through conversations with artificial intelligencecited by 2
  35. 2025PRISON: Unmasking the Criminal Potential of Large Language Modelscited by 2
  36. 2025Tailored untruths: How personalisation challenges LLM safeguardscited by 2
  37. 2026An Experimental Comparison of the Most Popular Approaches to Fake News Detectioncited by 2
  38. 2026AI advice suppresses people's willingness to say "I don't know", even when the advice is wrong and accuracy is incentivizedcited by 2

50 most cited of 78 All 78 (JSON)