Metraipolis › archive › dc_75cba37fd231

The Belief Update Gate: Separating Inertia from Learning in Human-AI Interaction — arXiv:2608.20828

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.20828
License (as archived)
CC0-1.0
Archived
2026-10-18T10:27:29.179Z
SHA-256 of the archived text
bba677a42b40f30da3b62e37bbb94fe9bbb6e93ce100aa40cdcbc8090a265080
Stable URL of this page
https://metraipolis.com/documento/dc_75cba37fd231

How to cite

The Belief Update Gate: Separating Inertia from Learning in Human-AI Interaction — arXiv:2608.20828 — arXiv (en), https://arxiv.org/abs/2608.20828 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_75cba37fd231 (Metraipolis archive dc_75cba37fd231, sha256 bba677a42b40f30da3b62e37bbb94fe9bbb6e93ce100aa40cdcbc8090a265080)
BibTeX
@misc{dc75cba37fd231,
  title = {The Belief Update Gate: Separating Inertia from Learning in Human-AI Interaction — arXiv:2608.20828},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.20828},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_75cba37fd231; sha256 bba677a42b40f30da3b62e37bbb94fe9bbb6e93ce100aa40cdcbc8090a265080},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.20828. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Repeated human-AI interaction is often analyzed through pooled belief-updating slopes: users observe AI successes and failures, revise reported beliefs in the feedback-consistent direction, but appear conservative on average. We show that such averages can obscure an important distinction between whether an elicited belief report changes at all and how it changes conditional on movement. We refer to this measurement-aware decomposition as the belief update gate. Reanalyzing a multi-task human-AI decision-making dataset with 240 participants, 7,200 trials, and three task domains, we find substantial non-movement in reported beliefs: 67.3% of trial-level belief changes are exactly zero, and 76.4% are smaller than five percentage points. Separating non-moving from moving reports changes the descriptive interpretation of pooled conservatism: the within-trajectory slope rises from 0.494 overall to 0.949 among rows with nonzero movement. Since this latter estimate conditions on observed movement, we interpret it as a descriptive decomposition rather than as evidence of a near-Bayesian latent learning process. Complementary hurdle style analyses (i.e., modeling zero vs. non-zero changes before predicting update magnitude) show that the absolute discrepancy between feedback and entering belief predicts whether a report changes, while the signed feedback discrepancy predicts the direction and magnitude of change among reports that move. Importantly, observed non-movement does not distinguish genuine latent belief inertia from small unexpressed updates, rounding, or other reporting processes. These findings show that calibration analyses of repeated human--AI interaction should distinguish visible non-movement in elicited belief reports from updating conditional on movement rather than treating reported beliefs as a single continuous updating process.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-24 in cs.HC).
Categorie arXiv: Human-Computer Interaction (cs.HC).
Pagina del lavoro: https://arxiv.org/abs/2608.20828 — 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 2026-10-18T10:27:20.503Z dalla pagina https://arxiv.org/catchup/cs.HC/2026-08-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).