mlsanityData to 14 Oct 2026

Defending Against Neural Fake News

arXiv 1905.12616 ↗First posted 29 May 2019cs.CL cs.CYcited by 559

Not on the map. Why?

Cited by 49 in LLM safety and security, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Recent progress in natural language generation has raised dual-use concerns. While applications like summarization and translation are positive, the underlying technology also might enable adversaries to generate neural fake news: targeted propaganda that closely mimics the style of real news. Modern computer security relies on careful threat modeling: identifying potential threats and vulnerabilities from an adversary's point of view, and exploring potential mitigations to these threats. Likewise, developing robust defenses against neural fake news requires us first to carefully investigate and characterize the risks of these models. We thus present a model for controllable text generation called Grover. Given a headline like `Link Found Between Vaccines and Autism,' Grover can generate the rest of the article; humans find these generations to be more trustworthy than human-written disinformation. Developing robust verification techniques against generators like Grover is critical. We find that best current discriminators can classify neural fake news from real, human-written, news with 73% accuracy, assuming access to a moderate level of training data. Counterintuitively, the best defense against Grover turns out to be Grover itself, with 92% accuracy, demonstrating the importance of public release of strong generators. We investigate these results further, showing that exposure bias -- and sampling strategies that alleviate its effects -- both leave artifacts that similar discriminators can pick up on. We conclude by discussing ethical issues regarding the technology, and plan to release Grover publicly, helping pave the way for better detection of neural fake news.

Key facts. Cited by 559 papers in the map (data through 14 Oct 2026). First posted on arXiv 29 May 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2020: 1; 2021: 85; 2022: 75; 2023: 142; 2024: 118; 2025: 93; 2026: 45.

559 papers.

Sort:

By area:

  1. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  2. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,975
  3. 2023A Survey of Large Language Modelscited by 2,576
  4. 2021Ethical and social risks of harm from Language Modelscited by 966
  5. 2023The Flan Collection: Designing Data and Methods for Effective Instruction Tuningcited by 739
  6. 2023DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvaturecited by 726
  7. 2023A Watermark for Large Language Modelscited by 725
  8. 2021Deduplicating Training Data Makes Language Models Bettercited by 714
  9. 2023In-Context Retrieval-Augmented Language Modelscited by 702
  10. 2021Retrieval Augmentation Reduces Hallucination in Conversationcited by 692
  11. 2023A Comprehensive Overview of Large Language Modelscited by 648
  12. 2022Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Modelcited by 559
38 more
  1. 2022InCoder: A Generative Model for Code Infilling and Synthesiscited by 498
  2. 2021Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpuscited by 492
  3. 2021MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontierscited by 470
  4. 2023Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defensecited by 429
  5. 2021A Survey on Automated Fact-Checkingcited by 378
  6. 2024Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Modelscited by 339
  7. 2023Data Selection for Language Models via Importance Resamplingcited by 329
  8. 2021MERLOT: Multimodal Neural Script Knowledge Modelscited by 311
  9. 2023Tool Learning with Foundation Modelscited by 302
  10. 2023Provable Robust Watermarking for AI-Generated Textcited by 299
  11. 2021All That's 'Human' Is Not Gold: Evaluating Human Evaluation of Generated Textcited by 287
  12. 2023Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attackscited by 278
  13. 2024Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Textcited by 263
  14. 2024Continual Learning of Large Language Models: A Comprehensive Surveycited by 234
  15. 2021Mind the Gap: Assessing Temporal Generalization in Neural Language Modelscited by 230
  16. 2023Undetectable Watermarks for Language Modelscited by 226
  17. 2022Factuality Enhanced Language Models for Open-Ended Text Generationcited by 202
  18. 2022SSD-LM: Semi-autoregressive Simplex-based Diffusion Language Model for Text Generation and Modular Controlcited by 194
  19. 2022Branch-Train-Merge: Embarrassingly Parallel Training of Expert Language Modelscited by 191
  20. 2023RADAR: Robust AI-Text Detection via Adversarial Learningcited by 190
  21. 2022MERLOT Reserve: Neural Script Knowledge through Vision and Language and Soundcited by 184
  22. 2023Can LLM-Generated Misinformation Be Detected?cited by 177
  23. 2021Towards Continual Knowledge Learning of Language Modelscited by 174
  24. 2021The Values Encoded in Machine Learning Researchcited by 172
  25. 2021Hurdles to Progress in Long-form Question Answeringcited by 167
  26. 2024Monitoring AI-Modified Content at Scale: A Case Study on the Impact of ChatGPT on AI Conference Peer Reviewscited by 164
  27. 2021Counterfactual Memorization in Neural Language Modelscited by 156
  28. 2022Repairing the Cracked Foundation: A Survey of Obstacles in Evaluation Practices for Generated Textcited by 155
  29. 2023Co-Writing with Opinionated Language Models Affects Users' Viewscited by 148
  30. 2023Should ChatGPT be Biased? Challenges and Risks of Bias in Large Language Modelscited by 148
  31. 2023Who Wrote this Code? Watermarking for Code Generationcited by 141
  32. 2021A Token-level Reference-free Hallucination Detection Benchmark for Free-form Text Generationcited by 138
  33. 2021DEMix Layers: Disentangling Domains for Modular Language Modelingcited by 132
  34. 2022Language Models as Agent Modelscited by 132
  35. 2023MAGE: Machine-generated Text Detection in the Wildcited by 132
  36. 2021AMMUS : A Survey of Transformer-based Pretrained Models in Natural Language Processingcited by 131
  37. 2024Attacks, Defenses and Evaluations for LLM Conversation Safety: A Surveycited by 130
  38. 2023DNA-GPT: Divergent N-Gram Analysis for Training-Free Detection of GPT-Generated Textcited by 129

50 most cited of 559 All 559 (JSON)