发表机构
University of Turku（图尔库大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对现有自动访谈系统的不足，提出基于本地LLM的证据可追溯动态访谈者架构，经246名参与者评估，其自适应组件运行稳定，访谈体验获积极反馈。
AI 中文摘要
自动访谈者和对话智能体越来越多地被应用于研究、招聘、客户服务和教育领域。然而，许多现有系统依赖固定的问题序列，且在不考虑参与者知识水平的情况下提供有限的基于上下文的个性化，这可能导致后续问题重复或不相关。因此，需要一种自适应访谈系统，该系统能够调整问题深度，同时保持对话的连续性和语义进展。为解决这一问题，本文提出了一种具备证据可追溯性的动态访谈者架构，该架构使用本地部署的大语言模型（LLM），并在整个对话过程中根据参与者的回答和不断变化的上下文持续调整访谈内容。该访谈者实时分析参与者的专业能力，以生成符合其知识水平的问题、表达清晰的回答以及支持对话连续性的流畅过渡消息。一个由五个模块组成的提示驱动架构和持久的访谈状态记录为这些功能提供支持。该访谈者在246名参与者中进行了评估：专业能力分析模块（M3）与独立报告的参与者专业能力的精确一致性为78.9%，加权Cohen's K值为0.80；迭代问题生成模块（M4）表现出强烈的专业能力-问题复杂度关联（相关系数r=0.79，p<0.001）；参与者报告的问题相关性平均得分为4.41、参与度平均得分为4.32、满意度平均得分为4.38，这表明该架构的自适应组件按预期功能运行，同时参与者对访谈体验持积极态度。
英文摘要
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.
CommentsAccepted 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
