Metraipolis › archive › dc_5d0958d2c176

Is That Clear? The Impacts of Clarifying Questions on Human-LLM Interaction — arXiv:2611.01087

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.01087
License (as archived)
CC0-1.0
Archived
2026-11-03T18:34:47.890Z
SHA-256 of the archived text
964bfeab4711e23c7171a33a77ad70edad857806dc260108ab7a7930880f53bc
Stable URL of this page
https://metraipolis.com/documento/dc_5d0958d2c176

How to cite

Is That Clear? The Impacts of Clarifying Questions on Human-LLM Interaction — arXiv:2611.01087 — arXiv (en), https://arxiv.org/abs/2611.01087 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5d0958d2c176 (Metraipolis archive dc_5d0958d2c176, sha256 964bfeab4711e23c7171a33a77ad70edad857806dc260108ab7a7930880f53bc)
BibTeX
@misc{dc5d0958d2c176,
  title = {Is That Clear? The Impacts of Clarifying Questions on Human-LLM Interaction — arXiv:2611.01087},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.01087},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5d0958d2c176; sha256 964bfeab4711e23c7171a33a77ad70edad857806dc260108ab7a7930880f53bc},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01087. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

LLM assistants increasingly ask clarifying questions (CQs) to elicit preferences and tailor recommendations. Although prior work emphasizes improvements in answer quality and user experience, how CQs shape users' subsequent engagement and reliance remains unclear. We conducted a controlled experiment (N=180) across six everyday decision scenarios, comparing human-LLM interaction with and without CQs. We further manipulated whether responses violated explicit constraints and whether violations occurred in the sub-decisions the CQs addressed, while preserving elicited preferences. CQs increased perceived understanding and satisfaction, yet participants spent less time reviewing and evaluating responses and accepted more responses unchanged, including erroneous ones. Within the CQ condition, participants more often accepted responses containing CQ-adjacent violations than nonadjacent violations. These findings demonstrate that LLM's proactive CQs shape subsequent engagement and reliance with preference elicitation. We discuss implications for designing and evaluating proactive assistants that support continued user scrutiny of answers alongside personalization.

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/2611.01087 — 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 2026-11-03T18:12:37.965Z dalla pagina https://arxiv.org/list/cs.HC/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).