Source record

Published by arXiv cs.HC (T1 source). The original is at https://arxiv.org/abs/2610.27333.

Pipeline notes

The summary and note below are generated by the signal pipeline — they are Beyond Desk’s reading, not quotations from the source.

Paper presents Rehearsim, a research probe using LLM-simulated participants as materials for qualitative interview rehearsal rather than human substitutes. A study with 21 researchers shows it helps surface assumptions, revise target populations, and develop probes, while revealing risks such as concealment of weak questions and interpretive anchoring.

Concrete inspectable-rehearsal framework with traceability and contestability, plus documented risks from a 21-researcher empirical study — directly applicable to qualitative workflows using AI.

Cited by

No citations on record.