Eroding the Truth-Default: A Causal Analysis of Human Susceptibility to Foundation Model Hallucinations and Disinformation in the Wild
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914323889127424 |
|---|---|
| author | Loth, Alexander Kappes, Martin Pahl, Marc-Oliver |
| author_facet | Loth, Alexander Kappes, Martin Pahl, Marc-Oliver |
| contents | 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 framework that decouples "authenticity" from "attribution" to investigate the mechanisms of human susceptibility. Analyzing 918 evaluations across five FMs (including GPT-4 and Llama-2), we employ Structural Causal Models (SCMs) as a principal framework for formulating testable causal hypotheses about detection accuracy.
Contrary to partisan narratives, we find that political orientation shows a negligible association with detection performance ($r=-0.10$). Instead, "fake news familiarity" emerges as a candidate mediator ($r=0.35$), suggesting that exposure may function as adversarial training for human discriminators. We identify a "fluency trap" where GPT-4 outputs (HumanMachineScore: 0.20) bypass Source Monitoring mechanisms, rendering them indistinguishable from human text.
These findings suggest that "pre-bunking" interventions should target cognitive source monitoring rather than demographic segmentation to ensure trustworthy information ecosystems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_22871 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Eroding the Truth-Default: A Causal Analysis of Human Susceptibility to Foundation Model Hallucinations and Disinformation in the Wild Loth, Alexander Kappes, Martin Pahl, Marc-Oliver Computers and Society Artificial Intelligence Computation and Language Human-Computer Interaction I.2.7; H.5.2; K.4.1 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 framework that decouples "authenticity" from "attribution" to investigate the mechanisms of human susceptibility. Analyzing 918 evaluations across five FMs (including GPT-4 and Llama-2), we employ Structural Causal Models (SCMs) as a principal framework for formulating testable causal hypotheses about detection accuracy. Contrary to partisan narratives, we find that political orientation shows a negligible association with detection performance ($r=-0.10$). Instead, "fake news familiarity" emerges as a candidate mediator ($r=0.35$), suggesting that exposure may function as adversarial training for human discriminators. We identify a "fluency trap" where GPT-4 outputs (HumanMachineScore: 0.20) bypass Source Monitoring mechanisms, rendering them indistinguishable from human text. These findings suggest that "pre-bunking" interventions should target cognitive source monitoring rather than demographic segmentation to ensure trustworthy information ecosystems. |
| title | Eroding the Truth-Default: A Causal Analysis of Human Susceptibility to Foundation Model Hallucinations and Disinformation in the Wild |
| topic | Computers and Society Artificial Intelligence Computation and Language Human-Computer Interaction I.2.7; H.5.2; K.4.1 |
| url | https://arxiv.org/abs/2601.22871 |