Metraipolis › archive › dc_6f02bb67a102
Can LLMs Trust Appropriately? Evaluating Calibrated Reliance on Imperfect Partners — arXiv:2610.34107
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.34107
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-27T07:57:27.781Z
- SHA-256 of the archived text
9598f07ff213709836ccb763c8f2ffa2ee5612887a6a7d2a5c98e9a3616ff719- Stable URL of this page
https://metraipolis.com/documento/dc_6f02bb67a102
How to cite
Can LLMs Trust Appropriately? Evaluating Calibrated Reliance on Imperfect Partners — arXiv:2610.34107 — arXiv (en), https://arxiv.org/abs/2610.34107 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6f02bb67a102 (Metraipolis archive dc_6f02bb67a102, sha256 9598f07ff213709836ccb763c8f2ffa2ee5612887a6a7d2a5c98e9a3616ff719)
BibTeX
@misc{dc6f02bb67a102,
title = {Can LLMs Trust Appropriately? Evaluating Calibrated Reliance on Imperfect Partners — arXiv:2610.34107},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.34107},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6f02bb67a102; sha256 9598f07ff213709836ccb763c8f2ffa2ee5612887a6a7d2a5c98e9a3616ff719},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.34107. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large language models increasingly collaborate with humans and peer AI agents whose contributions may be incomplete, inconsistent, or incorrect. Effective collaboration requires calibrated trust, whereby decisions to rely on, verify, or assist a partner adapt rationally as empirical evidence accumulates. We investigate whether models translate partner evidence into appropriate reliance policies. We introduce a benchmark of 324 scenarios across 23 collaboration categories. Each scenario involves three sequential decisions with explicit transition dynamics, feedback emissions, and cost schedules, permitting exact analytical evaluation of choices against their expected consequences over the remaining interaction. Evaluating seven models alongside 36 controlled-history probes, we dissociate evidence sensitivity from normatively appropriate action. While the strongest frontier model approaches near-optimal decisions, other models exhibit recurring pathologies: procuring excessive safeguards, purchasing verification tests with zero expected value of information, prioritizing immediate savings over cooperative learning, and misallocating assistance to suboptimal channels. Supplying explicit posterior distributions resolves certain errors while introducing new failure modes. Calibrated trust in autonomous agents critically demands coupling empirical evidence with forward-looking decision utility. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL); Human-Computer Interaction (cs.HC). Pagina del lavoro: https://arxiv.org/abs/2610.34107 — 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 2026-10-27T07:55:30.679Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).