# Automatic Detection of Generated Text is Easiest when Humans are Fooled

arXiv: https://arxiv.org/abs/1911.00650 · HTML: https://mlsanity.com/paper/1911.00650/

## Key facts

- Cited by 261 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Nov 2019.

## Built on by (most cited first, 30 of 261)

- [DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature](https://mlsanity.com/paper/2301.11305/) (2023)
- [MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontiers](https://mlsanity.com/paper/2102.01454/) (2021)
- [Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense](https://mlsanity.com/paper/2303.13408/) (2023)
- [Can AI-Generated Text be Reliably Detected?](https://mlsanity.com/paper/2303.11156/) (2023)
- [All That's 'Human' Is Not Gold: Evaluating Human Evaluation of Generated Text](https://mlsanity.com/paper/2107.00061/) (2021)
- [Fast-DetectGPT: Efficient Zero-Shot Detection of Machine-Generated Text via Conditional Probability Curvature](https://mlsanity.com/paper/2310.05130/) (2023)
- [DetectLLM: Leveraging Log Rank Information for Zero-Shot Detection of Machine-Generated Text](https://mlsanity.com/paper/2306.05540/) (2023)
- [RADAR: Robust AI-Text Detection via Adversarial Learning](https://mlsanity.com/paper/2307.03838/) (2023)
- [GPT detectors are biased against non-native English writers](https://mlsanity.com/paper/2304.02819/) (2023)
- [Monitoring AI-Modified Content at Scale: A Case Study on the Impact of ChatGPT on AI Conference Peer Reviews](https://mlsanity.com/paper/2403.07183/) (2024)
- [RAID: A Shared Benchmark for Robust Evaluation of Machine-Generated Text Detectors](https://mlsanity.com/paper/2405.07940/) (2024)
- [Repairing the Cracked Foundation: A Survey of Obstacles in Evaluation Practices for Generated Text](https://mlsanity.com/paper/2202.06935/) (2022)
- [Who Wrote this Code? Watermarking for Code Generation](https://mlsanity.com/paper/2305.15060/) (2023)
- [DNA-GPT: Divergent N-Gram Analysis for Training-Free Detection of GPT-Generated Text](https://mlsanity.com/paper/2305.17359/) (2023)
- [The Science of Detecting LLM-Generated Texts](https://mlsanity.com/paper/2303.07205/) (2023)
- [Truncation Sampling as Language Model Desmoothing](https://mlsanity.com/paper/2210.15191/) (2022)
- [M4: Multi-generator, Multi-domain, and Multi-lingual Black-Box Machine-Generated Text Detection](https://mlsanity.com/paper/2305.14902/) (2023)
- [TURINGBENCH: A Benchmark Environment for Turing Test in the Age of Neural Text Generation](https://mlsanity.com/paper/2109.13296/) (2021)
- [Mapping the Increasing Use of LLMs in Scientific Papers](https://mlsanity.com/paper/2404.01268/) (2024)
- [Unbiased Watermark for Large Language Models](https://mlsanity.com/paper/2310.10669/) (2023)
- [Human heuristics for AI-generated language are flawed](https://mlsanity.com/paper/2206.07271/) (2022)
- [A Survey on LLM-Generated Text Detection: Necessity, Methods, and Future Directions](https://mlsanity.com/paper/2310.14724/) (2023)
- [The Perils of Using Mechanical Turk to Evaluate Open-Ended Text Generation](https://mlsanity.com/paper/2109.06835/) (2021)
- [MGTBench: Benchmarking Machine-Generated Text Detection](https://mlsanity.com/paper/2303.14822/) (2023)
- [Language Model Behavior: A Comprehensive Survey](https://mlsanity.com/paper/2303.11504/) (2023)
- [Ghostbuster: Detecting Text Ghostwritten by Large Language Models](https://mlsanity.com/paper/2305.15047/) (2023)
- [Identifying and Mitigating the Security Risks of Generative AI](https://mlsanity.com/paper/2308.14840/) (2023)
- [Testing of Detection Tools for AI-Generated Text](https://mlsanity.com/paper/2306.15666/) (2023)
- [Three Bricks to Consolidate Watermarks for Large Language Models](https://mlsanity.com/paper/2308.00113/) (2023)
- [A Survey of GPT-3 Family Large Language Models Including ChatGPT and GPT-4](https://mlsanity.com/paper/2310.12321/) (2023)

## Abstract (arXiv)

Recent advancements in neural language modelling make it possible to rapidly generate vast amounts of human-sounding text. The capabilities of humans and automatic discriminators to detect machine-generated text have been a large source of research interest, but humans and machines rely on different cues to make their decisions. Here, we perform careful benchmarking and analysis of three popular sampling-based decoding strategies---top-k, nucleus sampling, and untruncated random sampling---and show that improvements in decoding methods have primarily optimized for fooling humans. This comes at the expense of introducing statistical abnormalities that make detection easy for automatic systems. We also show that though both human and automatic detector performance improve with longer excerpt length, even multi-sentence excerpts can fool expert human raters over 30% of the time. Our findings reveal the importance of using both human and automatic detectors to assess the humanness of text generation systems.