Metraipolis › archive › dc_0113ab3faeaa

Think Once, Reflect Twice: How Feedback Shapes Human-AI Collaboration — arXiv:2610.19991

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.19991
License (as archived)
CC0-1.0
Archived
2026-10-15T21:46:47.716Z
SHA-256 of the archived text
688f4e916cff8d75e0a12dc932ff90f1bb0861c6a4b5295bd8f8b67020bdb4e6
Stable URL of this page
https://metraipolis.com/documento/dc_0113ab3faeaa

How to cite

Think Once, Reflect Twice: How Feedback Shapes Human-AI Collaboration — arXiv:2610.19991 — arXiv (en), https://arxiv.org/abs/2610.19991 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0113ab3faeaa (Metraipolis archive dc_0113ab3faeaa, sha256 688f4e916cff8d75e0a12dc932ff90f1bb0861c6a4b5295bd8f8b67020bdb4e6)
BibTeX
@misc{dc0113ab3faeaa,
  title = {Think Once, Reflect Twice: How Feedback Shapes Human-AI Collaboration — arXiv:2610.19991},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.19991},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0113ab3faeaa; sha256 688f4e916cff8d75e0a12dc932ff90f1bb0861c6a4b5295bd8f8b67020bdb4e6},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.19991. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

As artificial intelligence (AI) increasingly supports human decision-making in high-stakes domains, designing effective human-AI collaboration becomes critical. Successful collaboration requires humans to reflect on decision-making processes and adjust their strategies accordingly. Current research typically investigates interventions, such as explainable AI, that target reflection during the decision-making process (reflection-in-action). Less attention has been given to retrospective examination of decisions (reflection-on-action). This work explores reflection-on-action by studying the impact of feedback on reliance behavior and human-AI team performance. Specifically, we investigate feedback interventions targeting overrides of AI advice through a behavioral study (N=244). We find that such feedback influences reflection-on-action, while unidirectional feedback risks reducing subsequent reflection-in-action. Furthermore, we identify opposing shifts in reliance behavior that leave overall human-AI team performance unchanged but show context-dependent effects. Balanced feedback did not show these risks, preserving both concurrent and retrospective reflection, offering insights for designing for appropriate reliance on AI.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.HC, nuovi lavori del giorno).
Categorie arXiv: Human-Computer Interaction (cs.HC).
Pagina del lavoro: https://arxiv.org/abs/2610.19991 — 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 2026-10-15T21:33:59.691Z dalla pagina https://arxiv.org/list/cs.HC/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).