Reproduce “PolyInterview: An LLM-based Platform for Immersive Mock Interview Practice with Comprehensive Multimodal Assessment” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Zhiyuan Wen, Jiannong Cao, Kelly Chan, Zijian Wang, Chen Chen, Xiaoyun Liu, Jianing Yin, Zhuo Li
Researchers from The Hong Kong Polytechnic University developed PolyInterview, an LLM-based platform offering immersive mock interview practice. It generates personalized, role-adaptive questions and provides comprehensive, evidence-linked feedback based on multimodal assessment of textual, vocal, and non-verbal cues, demonstrating strong question relevance and actionable recommendations in expert evaluations.
Key insights
- Integrating LLMs for adaptive questioning with multimodal (text, audio, video) assessment by VLMs and speech models enables a comprehensive and immersive mock interview experience.
- Personalizing question generation based on job descriptions and candidate CVs, combined with dynamic, answer-aware follow-ups, enhances the relevance and realism of practice.
- Grounding the hierarchical assessment and feedback in established frameworks (KSA, STAR) allows for transparent, actionable recommendations linked directly to specific behaviors and evidence.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.