SimInterview: Transforming Business Education through Large Language Model-Based Simulated Multilingual Interview Training System
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916902462291968 |
|---|---|
| author | Nguyen, Truong Thanh Hung Nguyen, Tran Diem Quynh Cao, Hoang Loc Tran, Thi Cam Thanh Truong, Thi Cam Mai Cao, Hung |
| author_facet | Nguyen, Truong Thanh Hung Nguyen, Tran Diem Quynh Cao, Hoang Loc Tran, Thi Cam Thanh Truong, Thi Cam Mai Cao, Hung |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_11873 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SimInterview: Transforming Business Education through Large Language Model-Based Simulated Multilingual Interview Training System Nguyen, Truong Thanh Hung Nguyen, Tran Diem Quynh Cao, Hoang Loc Tran, Thi Cam Thanh Truong, Thi Cam Mai Cao, Hung Computers and Society Artificial Intelligence Human-Computer Interaction Multimedia 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. |
| title | SimInterview: Transforming Business Education through Large Language Model-Based Simulated Multilingual Interview Training System |
| topic | Computers and Society Artificial Intelligence Human-Computer Interaction Multimedia |
| url | https://arxiv.org/abs/2508.11873 |