# GPT-4 is judged more human than humans in displaced and inverted Turing tests

arXiv: https://arxiv.org/abs/2407.08853 · HTML: https://mlsanity.com/paper/2407.08853/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 37 references that are in the map.
- First posted on arXiv 11 Jul 2024.

## Builds on (most cited first, 14 of 14)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature](https://mlsanity.com/paper/2301.11305/) (2023)
- [Release Strategies and the Social Impacts of Language Models](https://mlsanity.com/paper/1908.09203/) (2019)
- [GLTR: Statistical Detection and Visualization of Generated Text](https://mlsanity.com/paper/1906.04043/) (2019)
- [Automatic Detection of Generated Text is Easiest when Humans are Fooled](https://mlsanity.com/paper/1911.00650/) (2019)
- [TweepFake: about Detecting Deepfake Tweets](https://mlsanity.com/paper/2008.00036/) (2020)
- [People cannot distinguish GPT-4 from a human in a Turing test](https://mlsanity.com/paper/2405.08007/) (2024)
- [Fighting Fire with Fire: Can ChatGPT Detect AI-generated Text?](https://mlsanity.com/paper/2308.01284/) (2023)
- [Does GPT-4 pass the Turing test?](https://mlsanity.com/paper/2310.20216/) (2023)
- [As Good As A Coin Toss: Human detection of AI-generated images, videos, audio, and audiovisual stimuli](https://mlsanity.com/paper/2403.16760/) (2024)
- [Game of Tones: Faculty detection of GPT-4 generated content in university assessments](https://mlsanity.com/paper/2305.18081/) (2023)
- [Deceiving computers in Reverse Turing Test through Deep Learning](https://mlsanity.com/paper/2006.11373/) (2020)

## Built on by (most cited first, 8 of 8)

- [Lies, Damned Lies, and Distributional Language Statistics: Persuasion and Deception with Large Language Models](https://mlsanity.com/paper/2412.17128/) (2024)
- [Assessing LLMs in Art Contexts: Critique Generation and Theory of Mind Evaluation](https://mlsanity.com/paper/2504.12805/) (2025)
- [How Open Must Language Models be to Enable Reliable Scientific Inference?](https://mlsanity.com/paper/2603.26539/) (2026)
- [WHERE and WHICH: Iterative Debate for Biomedical Synthetic Data Augmentation](https://mlsanity.com/paper/2503.23673/) (2025)
- [Human or Machine? A Preliminary Turing Test for Speech-to-Speech Interaction](https://mlsanity.com/paper/2602.24080/) (2026)
- [Conversation Games and a Strategic View of the Turing Test](https://mlsanity.com/paper/2501.18455/) (2025)
- [Identity from the Outside: A Conceptual Framework and Research Program for AI Personality Clones](https://mlsanity.com/paper/2608.11225/) (2026)
- [AwarenessBench: Assessing Cognitive Capabilities of Language Models](https://mlsanity.com/paper/2609.35409/) (2026)

## Abstract (arXiv)

Everyday AI detection requires differentiating between people and AI in informal, online conversations. In many cases, people will not interact directly with AI systems but instead read conversations between AI systems and other people. We measured how well people and large language models can discriminate using two modified versions of the Turing test: inverted and displaced. GPT-3.5, GPT-4, and displaced human adjudicators judged whether an agent was human or AI on the basis of a Turing test transcript. We found that both AI and displaced human judges were less accurate than interactive interrogators, with below chance accuracy overall. Moreover, all three judged the best-performing GPT-4 witness to be human more often than human witnesses. This suggests that both humans and current LLMs struggle to distinguish between the two when they are not actively interrogating the person, underscoring an urgent need for more accurate tools to detect AI in conversations.