PolyInterview: An LLM-based Platform for Immersive Mock Interview Practice with Comprehensive Multimodal Assessment
Quick Answer
PolyInterview is an LLM-based platform that enhances mock interview preparation through tailored questions and multimodal assessments, achieving a 93.7% alignment with job descriptions.
Quick Take
It features a digital human interviewer and evaluates responses across 13 behavioral features, providing actionable feedback linked to the KSA and STAR frameworks.
Key Points
- Generates tailored interview questions based on job descriptions and CVs.
- Conducts multi-turn spoken interviews with a digital human interviewer.
- Evaluates responses on content, vocal delivery, and non-verbal behavior.
- Aggregates 13 behavioral features into 10 assessment aspects.
- Publicly accessible with over 1,500 interview sessions recorded.
Paper Resources
📖 Reader Mode
~2 min readAbstract: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.
| Comments: | 10 pages, 7 figures, and 4 tables |
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2607.10310 [cs.CL] |
| (or arXiv:2607.10310v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2607.10310 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Zijian Wang [view email]
[v1]
Sat, 11 Jul 2026 13:33:50 UTC (9,789 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CL
See more →TriAgent: Divergence-Aware Committees for Cost-Efficient Financial Sentiment Analysis
TriAgent introduces a cost-efficient multi-agent system for financial sentiment analysis, combining VADER, FinBERT, and Qwen2.5. It achieves an F1 score of ~0.87 with significant savings of $9.3M/year at a 10M-user scale compared to GPT-4o-mini, while also detecting hallucinations with an AUC of 0.90.