arXiv：cs.AI· Aisvarya Adeseye, Jouni Isoaho, Adeyemi Adeseye, Seppo Virtanen, Mohammad Tahir·· 3 小时前
基于本地 LLM 的证据可追溯动态访谈架构，用于专家自适应定性访谈
Evidence-Traceable Dynamic Interviewer Architecture for Expertise-Adaptive Qualitative Interviews Using Local LLMs
AI 导读
研究者提出一种证据可追溯动态访谈架构，基于本地部署的大语言模型，按受访者实时作答调整提问深度。该系统含五个提示词驱动模块与持久化访谈状态记录，在 246 名参与者中评估：专长画像模块（M3）与独立报告的参与者专长精确一致率为 78.9%，加权 Cohen's K 为 0.80；生成迭代问题模块（M4）呈现强专长-复杂度关联（p=.79，p<.001）。
正文
Abstract:Automated interviewers and conversational agents are increasingly used in research, recruitment, customer service, and education. However, many existing systems rely on fixed question sequences and provide limited context-based personalization without considering participants' knowledge, which can lead to repetitive or irrelevant follow-up questions. Therefore, there is a need for an adaptive interviewing system that can adjust question depth while maintaining conversational continuity and semantic progression. To address this, an Evidence-Traceable Dynamic Interviewer Architecture is presented using a locally hosted Large Language Model (LLM), with the interview continuously adapted throughout the entire conversation based on the participant's responses and evolving context. The interviewer profiles participants' expertise in real time to generate knowledge-appropriate questions, well-articulated responses, and smooth transition messages that support conversational continuity. A five-module prompt-driven architecture and persistent interview-state record support these functions. The interviewer was evaluated with 246 participants. Expertise Profiling module (M3) showed 78.9% exact agreement with independently reported participant expertise, with a weighted Cohen's K of 0.80. Generate Iterative Questions module (M4) showed a strong expertise-complexity association (p=.79, p<.001), and participants reported high relevance (mean 4.41), engagement (mean 4.32), and satisfaction (mean 4.38), providing evidence that the architecture's adaptive components operated consistently with their intended functions while participants reported a positive interview experience.
| Comments: | Accepted to be part of the book titled: AI in Education : Pedagogy, Ethics, and Society which will be published by Springer Nature in the Book series: Transactions on Computational Science and Computational Intelligence |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.11651 [cs.AI] |
| (or arXiv:2610.11651v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.11651 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Aisvarya Adeseye Mrs [view email]
[v1]
Thu, 8 Oct 2026 10:26:13 UTC (56,402 KB)
来源：arXiv：cs.AI · arxiv.org