Metraipolis › archive › dc_c534522cf620

When the Interviewer Is a Bot: Behavior, Breakdowns, and Trust in MLLM-Led Interviews — arXiv:2608.10412

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.10412
License (as archived)
CC0-1.0
Archived
2026-10-19T06:14:47.552Z
SHA-256 of the archived text
5a8256bfc84809ff97058b13a33915c3edfccf895cd2a0f27be2ab61f616a368
Stable URL of this page
https://metraipolis.com/documento/dc_c534522cf620

How to cite

When the Interviewer Is a Bot: Behavior, Breakdowns, and Trust in MLLM-Led Interviews — arXiv:2608.10412 — arXiv (en), https://arxiv.org/abs/2608.10412 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c534522cf620 (Metraipolis archive dc_c534522cf620, sha256 5a8256bfc84809ff97058b13a33915c3edfccf895cd2a0f27be2ab61f616a368)
BibTeX
@misc{dcc534522cf620,
  title = {When the Interviewer Is a Bot: Behavior, Breakdowns, and Trust in MLLM-Led Interviews — arXiv:2608.10412},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.10412},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c534522cf620; sha256 5a8256bfc84809ff97058b13a33915c3edfccf895cd2a0f27be2ab61f616a368},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.10412. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Semi-structured interviews are a cornerstone of qualitative research but remain labor-intensive. We report an empirical study of what actually happens when the interviewer is an off-the-shelf real-time multimodal LLM (MLLM). We built InterviewBot, a voice-based interviewing system that wraps a real-time MLLM with a researcher-authored outline, and deployed it not as a novel architecture but as a research instrument for observing default MLLM interviewing behavior. In a practice study (N=15), participants completed a bot-led semi-structured interview and then a human-led reflection session about that experience. We contribute (i) a turn-level behavioral analysis of an MLLM interviewer (N_turns=428) showing that it is acknowledgment-heavy but probe-light (deepening probes account for 4.9% of all turns), and that 28.7% of question-bearing turns pack multiple questions into one turn despite an explicit one-question-at-a-time instruction; (ii) an inductive catalogue of four data-collection breakdowns (information loss, premature termination, latency, and interruption) observed in a deployed rather than simulated system; and (iii) three social dynamics from participants' reflections: disclosure calibration, where reduced social pressure coincided with shallower elaboration; institutional legitimacy, where trust tracked perceived stakes and what delegation to AI signaled about the organizer rather than conversational competence; and conversational grounding, where content-grounded paraphrase, not generic social filler, was what participants read as listening. We conclude with design implications for depth control, transparent handoffs, and non-templated listening mechanisms in human-centered interview automation.

Tema degli esploratori: governance digitale e beni comuni (retro-catalogo arXiv: annunci del 2026-08-12 in cs.CY).
Categorie arXiv: Human-Computer Interaction (cs.HC) ; Computers and Society (cs.CY).
Pagina del lavoro: https://arxiv.org/abs/2608.10412 — 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 2026-10-19T06:09:53.624Z dalla pagina https://arxiv.org/catchup/cs.CY/2026-08-12?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).