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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Rathi, Ishika, Taylor, Sydney, Bergen, Benjamin K., Jones, Cameron R.
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909251652288512
author Rathi, Ishika
Taylor, Sydney
Bergen, Benjamin K.
Jones, Cameron R.
author_facet Rathi, Ishika
Taylor, Sydney
Bergen, Benjamin K.
Jones, Cameron R.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2407_08853
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle GPT-4 is judged more human than humans in displaced and inverted Turing tests
Rathi, Ishika
Taylor, Sydney
Bergen, Benjamin K.
Jones, Cameron R.
Human-Computer Interaction
Computation and Language
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.
title GPT-4 is judged more human than humans in displaced and inverted Turing tests
topic Human-Computer Interaction
Computation and Language
url https://arxiv.org/abs/2407.08853