用大模型打造多语言模拟面试系统，帮商科人才提升实战能力
SimInterview: Transforming Business Education through Large Language Model-Based Simulated Multilingual Interview Training System
- 基于大模型和检索增强生成，动态匹配简历与岗位需求
- 在英日双语市场验证，轻量级Gemma 3对话最生动，满意度高
- 支持文化适配、可解释性设计，适合求职训练与教育场景
商业面试准备既需理论基础又需软技能，但传统课堂难以提供个性化、跨文化的真实练习。本文提出SimInterview，一个基于大语言模型（LLM）的多语言模拟面试训练系统，专为应对人工智能变革下的职场需求而设计。系统利用LLM代理与合成AI技术，生成能实时对话的虚拟招聘官，通过检索增强生成（RAG）动态匹配个人简历与职位要求，覆盖多语言场景。系统基于OpenAI o3、Llama 4 Maverick、Gemma 3等模型，集成Whisper语音识别、GPT-SoVITS语音合成、Ditto扩散驱动的说话头生成模型及ChromaDB向量数据库，在英日市场实验中均显著提升面试准备度。大学生测试显示，系统评估与岗位要求高度一致，准确保留简历内容，且用户满意度高；其中轻量级Gemma 3模型生成的对话最为自然。定性分析发现，标准化的日文简历提升文档检索效果，英文简历多样性增加挑战；文化规范深刻影响追问策略。最后，系统提出可争议的AI设计，支持解释性、偏见检测与人工介入，以满足新兴监管要求。
原文摘要 · Abstract (English)
Business interview preparation demands both solid theoretical grounding and refined soft skills, yet conventional classroom methods rarely deliver the individualized, culturally aware practice employers currently expect. This paper introduces SimInterview, a large language model (LLM)-based simulated multilingual interview training system designed for business professionals entering the AI-transformed labor market. Our system leverages an LLM agent and synthetic AI technologies to create realistic virtual recruiters capable of conducting personalized, real-time conversational interviews. The framework dynamically adapts interview scenarios using retrieval-augmented generation (RAG) to match individual resumes with specific job requirements across multiple languages. Built on LLMs (OpenAI o3, Llama 4 Maverick, Gemma 3), integrated with Whisper speech recognition, GPT-SoVITS voice synthesis, Ditto diffusion-based talking head generation model, and ChromaDB vector databases, our system significantly improves interview readiness across English and Japanese markets. Experiments with university-level candidates show that the system consistently aligns its assessments with job requirements, faithfully preserves resume content, and earns high satisfaction ratings, with the lightweight Gemma 3 model producing the most engaging conversations. Qualitative findings revealed that the standardized Japanese resume format improved document retrieval while diverse English resumes introduced additional variability, and they highlighted how cultural norms shape follow-up questioning strategies. Finally, we also outlined a contestable AI design that can explain, detect bias, and preserve human-in-the-loop to meet emerging regulatory expectations.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。