Metraipolis › archive › dc_173ccebc2a6f

Towards Detecting AI-Assisted Responses in Online Surveys — arXiv:2609.17317

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.17317
License (as archived)
CC0-1.0
Archived
2026-10-15T19:19:29.775Z
SHA-256 of the archived text
7ffba838b531de0dd1aee43b72e292b6bdaf6d7c42d5a4b49e27330fff00825b
Stable URL of this page
https://metraipolis.com/documento/dc_173ccebc2a6f

How to cite

Towards Detecting AI-Assisted Responses in Online Surveys — arXiv:2609.17317 — arXiv (en), https://arxiv.org/abs/2609.17317 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_173ccebc2a6f (Metraipolis archive dc_173ccebc2a6f, sha256 7ffba838b531de0dd1aee43b72e292b6bdaf6d7c42d5a4b49e27330fff00825b)
BibTeX
@misc{dc173ccebc2a6f,
  title = {Towards Detecting AI-Assisted Responses in Online Surveys — arXiv:2609.17317},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.17317},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_173ccebc2a6f; sha256 7ffba838b531de0dd1aee43b72e292b6bdaf6d7c42d5a4b49e27330fff00825b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.17317. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

The use of LLMs to complete online surveys impacts the validity of survey-based research, but detecting such usage remains underexplored. We introduce an initial benchmark dataset, namely ASURRE, for AI-assisted survey participation to capture usage strategies ranging from full generation and revision to persona-grounded agentic completion. Controlled by these strategies, LLM-assisted survey responses are generated using multiple LLMs on three real-world surveys in different disciplines, paired with genuine human responses. Our evaluation of existing machine-generated text (MGT) detectors shows that naive AI usage is readily detectable, whereas persona-grounded agents that mimic entire respondents push detector performance toward chance. We further show that agentic completion cannot fully replicate respondent-level behaviour and leaves distinctive behavioural traces. While individual cues can be circumvented by targeted prompting, a simple few-shot, training-free aggregator over these cues improves mean AUROC by +0.14 over the best existing detector across agentic settings. Our project is available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-16 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL) ; Computers and Society (cs.CY).
Pagina del lavoro: https://arxiv.org/abs/2609.17317 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-15T18:32:32.869Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-16?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).