Can Humans Tell? A Dual-Axis Study of Human Perception of LLM-Generated News

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Loth, Alexander, Kappes, Martin, Pahl, Marc-Oliver
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910103057203200
author Loth, Alexander
Kappes, Martin
Pahl, Marc-Oliver
author_facet Loth, Alexander
Kappes, Martin
Pahl, Marc-Oliver
contents Can humans tell whether a news article was written by a person or a large language model (LLM)? We investigate this question using JudgeGPT, a study platform that independently measures source attribution (human vs. machine) and authenticity judgment (legitimate vs. fake) on continuous scales. From 2,318 judgments collected from 1,054 participants across content generated by six LLMs, we report five findings: (1) participants cannot reliably distinguish machine-generated from human-written text (p > .05, Welch's t-test); (2) this inability holds across all tested models, including open-weight models with as few as 7B parameters; (3) self-reported domain expertise predicts judgment accuracy (r = .35, p < .001) whereas political orientation does not (r = -.10, n.s.); (4) clustering reveals distinct response strategies ("Skeptics" vs. "Believers"); and (5) accuracy degrades after approximately 30 sequential evaluations due to cognitive fatigue. The answer, in short, is no: humans cannot reliably tell. These results indicate that user-side detection is not a viable defense and motivate system-level countermeasures such as cryptographic content provenance.
format Preprint
id arxiv_https___arxiv_org_abs_2604_03755
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Can Humans Tell? A Dual-Axis Study of Human Perception of LLM-Generated News
Loth, Alexander
Kappes, Martin
Pahl, Marc-Oliver
Computers and Society
Artificial Intelligence
Computation and Language
Human-Computer Interaction
H.5.2; K.4.2; I.2.7
Can humans tell whether a news article was written by a person or a large language model (LLM)? We investigate this question using JudgeGPT, a study platform that independently measures source attribution (human vs. machine) and authenticity judgment (legitimate vs. fake) on continuous scales. From 2,318 judgments collected from 1,054 participants across content generated by six LLMs, we report five findings: (1) participants cannot reliably distinguish machine-generated from human-written text (p > .05, Welch's t-test); (2) this inability holds across all tested models, including open-weight models with as few as 7B parameters; (3) self-reported domain expertise predicts judgment accuracy (r = .35, p < .001) whereas political orientation does not (r = -.10, n.s.); (4) clustering reveals distinct response strategies ("Skeptics" vs. "Believers"); and (5) accuracy degrades after approximately 30 sequential evaluations due to cognitive fatigue. The answer, in short, is no: humans cannot reliably tell. These results indicate that user-side detection is not a viable defense and motivate system-level countermeasures such as cryptographic content provenance.
title Can Humans Tell? A Dual-Axis Study of Human Perception of LLM-Generated News
topic Computers and Society
Artificial Intelligence
Computation and Language
Human-Computer Interaction
H.5.2; K.4.2; I.2.7
url https://arxiv.org/abs/2604.03755