PulseAugur
EN
LIVE 10:03:13

New framework reveals human susceptibility to AI hallucinations

By PulseAugur Editorial · [1 sources] ·

A new research paper introduces JudgeGPT and RogueGPT, a framework designed to investigate how humans fall prey to foundation model hallucinations and disinformation. The study analyzed 918 evaluations across five foundation models, including GPT-4 and Llama 2, and found that political orientation had a minimal impact on detection accuracy. Instead, familiarity with "fake news" emerged as a significant factor, suggesting that exposure can act as a form of adversarial training for human discernment. The research highlights a "fluency trap" where highly fluent outputs from models like GPT-4 become indistinguishable from human text, impairing source monitoring mechanisms. AI

IMPACT Highlights cognitive vulnerabilities to AI-generated disinformation, suggesting new approaches for 'pre-bunking' interventions.

RANK_REASON Academic paper detailing a new framework and analysis of human susceptibility to AI hallucinations. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CL →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

New framework reveals human susceptibility to AI hallucinations

How we ranked this

Signal score
1 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
Academic paper detailing a new framework and analysis of human susceptibility to AI hallucinations. [lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, safety
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
1 days old
Coverage has settled into its steady-state source set.

Full methodology in our editorial standards.

COVERAGE [1]

  1. arXiv cs.CL TIER_1 English(EN) · Alexander Loth, Martin Kappes, Marc-Oliver Pahl ·

    Eroding the Truth-Default: A Causal Analysis of Human Susceptibility to Foundation Model Hallucinations and Disinformation in the Wild

    arXiv:2601.22871v3 Announce Type: replace-cross Abstract: As foundation models (FMs) approach human-level fluency, distinguishing synthetic from organic content has become a key challenge for Trustworthy Web Intelligence. This paper presents JudgeGPT and RogueGPT, a dual-axis fra…

RELATED ENTITIES

RELATED TOPICS