PolyInterview: An LLM-based Platform for Immersive Mock Interview Practice with Comprehensive Multimodal Assessment
作者: Zhiyuan Wen, Jiannong Cao, Kelly Chan, Zijian Wang, Chen Chen, Xiaoyun Liu, Jianing Yin, Zhuo Li
分类: cs.CL
发布日期: 2026-07-20
💡 一句话要点
提出PolyInterview以解决面试准备中的实践不足问题
🎯 匹配领域: 支柱九:具身大模型 (Embodied Foundation Models)
关键词: 模拟面试 多模态评估 大型语言模型 个性化反馈 职业培训 求职准备
📋 核心要点
- 现有的面试准备方法存在频率低、成本高和缺乏适应性对话等问题,难以满足求职者的需求。
- PolyInterview通过生成定制化问题、进行多轮口语面试和综合评估,提供沉浸式的模拟面试体验。
- 实验结果显示,生成的问题在93.7%的情况下与匹配的职位描述更为一致,专家评估也认为反馈具有可操作性。
📝 摘要(中文)
准备求职面试对获得理想职位至关重要,但现实中的练习机会有限。现有系统通常只能部分满足需求,存在固定问题序列、有限沟通渠道及反馈缺乏证据等问题。本文提出PolyInterview,一个基于大型语言模型的沉浸式模拟面试平台,提供全面的多模态评估。该平台根据目标职位描述和简历生成定制问题,进行多轮口语面试,并评估回答内容、语音表达和非语言行为。评估结果与行为证据和可操作建议相链接,PolyInterview目前已公开访问,展示了强大的问题计划和可行反馈。
🔬 方法详解
问题定义:本文旨在解决求职者在面试准备中面临的实践机会不足和反馈不充分的问题。现有方法往往只能提供固定的问题序列,缺乏个性化和适应性。
核心思路:PolyInterview通过利用大型语言模型生成与职位描述和简历相关的定制问题,结合多轮口语面试和全面的多模态评估,提供更真实的模拟面试体验。
技术框架:该平台的整体架构包括问题生成模块、面试执行模块和评估反馈模块。问题生成模块根据用户的简历和职位描述生成问题,面试执行模块使用数字人类进行互动,评估反馈模块则分析用户的回答和表现。
关键创新:PolyInterview的创新在于其综合性评估方法,结合了内容、语音和非语言行为的多维度评估,与传统的单一反馈方式形成鲜明对比。
关键设计:在评估过程中,四个评估者生成13个行为特征,这些特征被聚合为10个评估方面和两个能力轨道,确保评估的全面性和准确性。
🖼️ 关键图片
📊 实验亮点
实验结果显示,PolyInterview生成的问题在93.7%的面试会话中与匹配的职位描述高度一致。此外,十位专家的评估结果表明,该平台提供了强有力的问题计划和可操作的反馈,显著提升了模拟面试的有效性。
🎯 应用场景
PolyInterview可广泛应用于求职培训、职业发展和教育领域,为求职者提供个性化的面试准备方案。其沉浸式的模拟面试体验和全面的评估反馈将帮助求职者提升面试技能,增强自信心,进而提高求职成功率。未来,该平台还可扩展至其他领域的技能培训和评估。
📄 摘要(原文)
Preparing for job interviews is important for securing desired positions, yet realistic practice remains difficult to access: real interviews are infrequent, expert mock coaching is costly, and self-practice offers neither adaptive dialogue nor structured assessment. Existing systems typically address only parts of this need through fixed question sequences, limited communication channels, or feedback with little supporting evidence. We present PolyInterview, an LLM-based platform for immersive mock interview practice with comprehensive multimodal assessment. PolyInterview uses the target job description and CV to generate questions tailored to the role and candidate, conducts multi-turn spoken interviews with a lip-synced digital human interviewer that asks answer-aware follow-up questions, and evaluates response content, vocal delivery, and non-verbal behavior. Four parallel evaluators produce 13 behavior-level features that are aggregated into 10 assessment aspects and two competency tracks. Guided by the KSA and STAR frameworks, the report links each score to behavioral evidence and actionable recommendations. PolyInterview is publicly accessible. Its current all-account snapshot contains 101 accounts, 1,564 interview sessions, 7,665 generated questions, and 1,422 five-stage question sets. Generated questions are more closely aligned with their matched job description than with cross-role job descriptions in 93.7% of sessions. An evaluation by ten experts found strong question plans and actionable feedback.