Metraipolis › archive › dc_0643ab5d0930

Confident, Not Wiser: The Dunning-Kruger Effect in Human-AI Interaction — arXiv:2609.31095

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.31095
License (as archived)
CC0-1.0
Archived
2026-10-08T02:09:47.552Z
SHA-256 of the archived text
4e6d29a2b3332af56beac93dd7ee1031a96bb0f86d83ccff9d3750fef5f0c00f
Stable URL of this page
https://metraipolis.com/documento/dc_0643ab5d0930

How to cite

Confident, Not Wiser: The Dunning-Kruger Effect in Human-AI Interaction — arXiv:2609.31095 — arXiv (en), https://arxiv.org/abs/2609.31095 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0643ab5d0930 (Metraipolis archive dc_0643ab5d0930, sha256 4e6d29a2b3332af56beac93dd7ee1031a96bb0f86d83ccff9d3750fef5f0c00f)
BibTeX
@misc{dc0643ab5d0930,
  title = {Confident, Not Wiser: The Dunning-Kruger Effect in Human-AI Interaction — arXiv:2609.31095},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.31095},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0643ab5d0930; sha256 4e6d29a2b3332af56beac93dd7ee1031a96bb0f86d83ccff9d3750fef5f0c00f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.31095. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

AI assistance can improve performance without improving self-assessment. We report a study (N=366) comparing Human alone and Human+AI performance on reasoning tasks, for which the AI model is benchmarked on the same items. Participants estimated global and block performance and rated confidence in their answers. Human+AI achieved higher scores, but self-estimates tracked performance weakly. Average overestimation was similar across groups, covering individual errors. Across tasks, confidence distinguished correct from incorrect answers less accurately in the Human+AI group, while within-task differences remained uncertain. The Dunning-Kruger pattern was found in both groups, with a larger observed contrast in Human+AI. Controls for score noise reduced but did not eliminate the pattern, with the controlled group difference remaining inconclusive. An extended computational account describes global and block estimates. Our findings distinguish performance augmentation from metacognitive augmentation and motivate interfaces that support verification, communicate task-specific AI model performance, and help users evaluate the quality of their joint work rather than produce answers.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-28 in cs.HC).
Categorie arXiv: Human-Computer Interaction (cs.HC).
Pagina del lavoro: https://arxiv.org/abs/2609.31095 — 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 2026-10-08T01:42:43.096Z dalla pagina https://arxiv.org/catchup/cs.HC/2026-09-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).