SparkMe: Adaptive Semi-Structured Interviewing for Qualitative Insight Discovery

• URL: http://arxiv.org/abs/2602.21136v1
• Date: Tue, 24 Feb 2026 17:33:02 GMT
• Title: SparkMe: Adaptive Semi-Structured Interviewing for Qualitative Insight Discovery
• Authors: David Anugraha, Vishakh Padmakumar, Diyi Yang,
• Abstract summary: We introduce SparkMe, a multi-agent interviewer that performs deliberative planning via simulated conversation rollouts to select questions with high expected utility.<n>We evaluate SparkMe through controlled experiments with LLM-based interviewees, showing that it achieves higher interview utility.<n>We further validate SparkMe in a user study with 70 participants across 7 professions on the impact of AI on their professions.
• Score: 55.50580661343875
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Qualitative insights from user experiences are critical for informing product and policy decisions, but collecting such data at scale is constrained by the time and availability of experts to conduct semi-structured interviews. Recent work has explored using large language models (LLMs) to automate interviewing, yet existing systems lack a principled mechanism for balancing systematic coverage of predefined topics with adaptive exploration, or the ability to pursue follow-ups, deep dives, and emergent themes that arise organically during conversation. In this work, we formulate adaptive semi-structured interviewing as an optimization problem over the interviewer's behavior. We define interview utility as a trade-off between coverage of a predefined interview topic guide, discovery of relevant emergent themes, and interview cost measured by length. Based on this formulation, we introduce SparkMe, a multi-agent LLM interviewer that performs deliberative planning via simulated conversation rollouts to select questions with high expected utility. We evaluate SparkMe through controlled experiments with LLM-based interviewees, showing that it achieves higher interview utility, improving topic guide coverage (+4.7% over the best baseline) and eliciting richer emergent insights while using fewer conversational turns than prior LLM interviewing approaches. We further validate SparkMe in a user study with 70 participants across 7 professions on the impact of AI on their workflows. Domain experts rate SparkMe as producing high-quality adaptive interviews that surface helpful profession-specific insights not captured by prior approaches. The code, datasets, and evaluation protocols for SparkMe are available as open-source at https://github.com/SALT-NLP/SparkMe.

Related papers

• Modular AI-Powered Interviewer with Dynamic Question Generation and Expertise Profiling [0.7349727826230863]
  This study presents an AI-powered interviewer that dynamically generates questions that are contextually appropriate and expertise aligned.<n>The interviewer is built on a locally hosted large language model (LLM) that generates coherent dialogue while preserving data privacy.<n>The proposed interviewer is a scalable, privacy-conscious solution that advances AI-assisted qualitative data collection.
  arXiv  Detail & Related papers  (2025-11-21T18:25:26Z)
• Do LLMs Recognize Your Latent Preferences? A Benchmark for Latent Information Discovery in Personalized Interaction [40.857161437572465]
  We introduce a benchmark for evaluating latent information discovery in personalized interaction.<n>The benchmark spans three progressively realistic settings: the classic 20 Questions game, Personalized Question Answering, and Personalized Text Summarization.<n>Our results reveal that while LLMs can indeed surface latent information through dialogue, their success varies dramatically with context.
  arXiv  Detail & Related papers  (2025-10-20T03:58:49Z)
• A Multi-To-One Interview Paradigm for Efficient MLLM Evaluation [63.76972456980632]
  We propose a multi-to-one interview paradigm for efficient MLLM evaluation.<n>Our framework consists of (i) a two-stage interview strategy with pre-interview and formal interview phases, (ii) dynamic adjustment of weights to ensure fairness, and (iii) an adaptive mechanism for question difficulty-level chosen.
  arXiv  Detail & Related papers  (2025-09-18T12:07:40Z)
• Requirements Elicitation Follow-Up Question Generation [0.5120567378386615]
  Large language models (LLMs) have exhibited state-of-the-art performance in multiple natural language processing tasks.<n>This study investigates the application of GPT-4o to generate follow-up interview questions during requirements elicitation.
  arXiv  Detail & Related papers  (2025-07-03T17:59:04Z)
• GuideLLM: Exploring LLM-Guided Conversation with Applications in Autobiography Interviewing [73.8469700907927]
  Large Language Models (LLMs) succeed in human-guided conversations such as instruction following and question answering.<n>In this study, we first characterize LLM-guided conversation into three fundamental components: Goal Navigation; (ii) Context Management; (iii) Empathetic Engagement.<n>We compare GuideLLM with 6 state-of-the-art LLMs such as GPT-4o and Llama-3-70b-Instruct, from the perspective of interviewing quality, and autobiography generation quality.
  arXiv  Detail & Related papers  (2025-02-10T14:11:32Z)
• LLM-as-an-Interviewer: Beyond Static Testing Through Dynamic LLM Evaluation [24.103034843158717]
  We introduce LLM-as-an-Interviewer, a novel paradigm for evaluating large language models (LLMs)<n>This approach leverages multi-turn interactions where the interviewer actively provides feedback on responses and poses follow-up questions to the evaluated LLM.<n>We apply the framework to evaluate six models on the MATH and DepthQA tasks.
  arXiv  Detail & Related papers  (2024-12-10T15:00:32Z)
• NewsInterview: a Dataset and a Playground to Evaluate LLMs' Ground Gap via Informational Interviews [65.35458530702442]
  We focus on journalistic interviews, a domain rich in grounding communication and abundant in data. We curate a dataset of 40,000 two-person informational interviews from NPR and CNN. LLMs are significantly less likely than human interviewers to use acknowledgements and to pivot to higher-level questions.
  arXiv  Detail & Related papers  (2024-11-21T01:37:38Z)
• AI Conversational Interviewing: Transforming Surveys with LLMs as Adaptive Interviewers [40.80290002598963]
  This study explores the potential of replacing human interviewers with large language models (LLMs) to conduct scalable conversational interviews.<n>We conducted a small-scale, in-depth study with university students who were randomly assigned to a conversational interview by either AI or human interviewers.<n>Various quantitative and qualitative measures assessed interviewer adherence to guidelines, response quality, participant engagement, and overall interview efficacy.
  arXiv  Detail & Related papers  (2024-09-16T16:03:08Z)
• MockLLM: A Multi-Agent Behavior Collaboration Framework for Online Job Seeking and Recruiting [29.676163697160945]
  We propose textbfMockLLM, a novel framework to generate and evaluate mock interview interactions.<n>By simulating both interviewer and candidate roles, MockLLM enables consistent and collaborative interactions for real-time and two-sided matching.<n>We evaluate MockLLM on real-world data Boss Zhipin, a major Chinese recruitment platform.
  arXiv  Detail & Related papers  (2024-05-28T12:23:16Z)
• Cue-CoT: Chain-of-thought Prompting for Responding to In-depth Dialogue Questions with LLMs [59.74002011562726]
  We propose a novel linguistic cue-based chain-of-thoughts (textitCue-CoT) to provide a more personalized and engaging response. We build a benchmark with in-depth dialogue questions, consisting of 6 datasets in both Chinese and English. Empirical results demonstrate our proposed textitCue-CoT method outperforms standard prompting methods in terms of both textithelpfulness and textitacceptability on all datasets.
  arXiv  Detail & Related papers  (2023-05-19T16:27:43Z)
• EZInterviewer: To Improve Job Interview Performance with Mock Interview Generator [60.2099886983184]
  EZInterviewer aims to learn from the online interview data and provides mock interview services to the job seekers. To address the low-resource challenge, EZInterviewer is trained on a very small set of interview dialogs.
  arXiv  Detail & Related papers  (2023-01-03T07:00:30Z)
• What should I Ask: A Knowledge-driven Approach for Follow-up Questions Generation in Conversational Surveys [63.51903260461746]
  We propose a novel task for knowledge-driven follow-up question generation in conversational surveys. We constructed a new human-annotated dataset of human-written follow-up questions with dialogue history and labeled knowledge. We then propose a two-staged knowledge-driven model for the task, which generates informative and coherent follow-up questions.
  arXiv  Detail & Related papers  (2022-05-23T00:57:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.