Tootfinder

When the Interviewer Is a Bot: Behavior, Breakdowns, and Trust in MLLM-Led Interviews
He Zhang, Kambinachi Chukwuma, ChanMin Kim, John M. Carroll
https://arxiv.org/abs/2608.10412 https://arxiv.org/pdf/2608.10412 https://arxiv.org/html/2608.10412
arXiv:2608.10412v1 Announce Type: new
Abstract: 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.
toXiv_bot_toot

Build-Authorized Evidence for Opaque Calls: A Fail-Closed Rewrite-Authority Boundary
Zhonghua Yi (Toka Language Research Group)
https://arxiv.org/abs/2607.18949 https://arxiv.org/pdf/2607.18949 https://arxiv.org/html/2607.18949
arXiv:2607.18949v1 Announce Type: new
Abstract: Detached semantic facts about opaque native providers do not by themselves justify compiler rewrites: rewrite authority must be confined to the accepted fact, selected provider and build, caller, callback environment, observation, and runtime target. We present a build-authorized path-effect interface that enforces this boundary through fail-closed authorization and link receipts. The design separates receipt closure, callback-environment closure, and projection identity, and passes accepted facts to LLVM through a narrow internal API. We use one-hop topology-load reuse as a minimal observable witness of authority, not as the optimization target.
A conservative LLVM consumer reuses a pointer observation only from a noalias root or one constant nonzero projection. Rocq models prove conditional refinement and authority non-amplification under explicit effect, alias, compiler/ABI, and target-resolution premises. We instantiate checked production with Toka: a source-summary gate emits exact LLVM IR, a separate IR checker accepts only a bounded topology-preserving subset, and only accepted IR is compiled into the receipt-bound provider object. A bounded static Darwin/arm64 profile also checks the final direct branch target.
Across issuer-declared readv, recvmsg, and Cairo boundaries, authorized IR retains each opaque call, reduces the relevant loads from two to one, and preserves observed results; mismatched providers, builds, callbacks, projections, and unsupported IR remain neutral. A libjpeg case is rejected because its callback environment is open, while a bound callback singleton demonstrates the supported closure rule. The contribution is a checked deployment-compiler boundary with an explicit trust and applicability frontier, not a uniquely expressive effect encoding or a new load-elimination algorithm.
toXiv_bot_toot