![[2602.20294] InterviewSim: A Scalable Framework for Interview-Grounded Personality Simulation](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
[2602.20294] InterviewSim: A Scalable Framework for Interview-Grounded Personality Simulation
Summary
The paper presents InterviewSim, a framework for simulating personalities using large language models grounded in real interview data, enhancing evaluation metrics for personality simulation.
Why It Matters
This research addresses the limitations of existing personality simulation methods by introducing a scalable framework that utilizes authentic interview data. This advancement is crucial for improving the accuracy and reliability of AI-generated personalities, which have applications in various fields including entertainment, customer service, and mental health.
Key Takeaways
- InterviewSim uses over 671,000 Q&A pairs from verified interviews to enhance personality simulation.
- The framework proposes four metrics for evaluating personality simulation: content similarity, factual consistency, personality alignment, and knowledge retention.
- Retrieval-augmented methods excel in capturing personality style, while chronological methods better preserve factual consistency.
- The findings provide actionable insights for selecting methods based on specific application requirements.
- This research contributes significantly to the field of personality simulation, offering a more grounded approach than traditional methods.
Computer Science > Computation and Language arXiv:2602.20294 (cs) [Submitted on 23 Feb 2026] Title:InterviewSim: A Scalable Framework for Interview-Grounded Personality Simulation Authors:Yu Li, Pranav Narayanan Venkit, Yada Pruksachatkun, Chien-Sheng Wu View a PDF of the paper titled InterviewSim: A Scalable Framework for Interview-Grounded Personality Simulation, by Yu Li and 2 other authors View PDF HTML (experimental) Abstract:Simulating real personalities with large language models requires grounding generation in authentic personal data. Existing evaluation approaches rely on demographic surveys, personality questionnaires, or short AI-led interviews as proxies, but lack direct assessment against what individuals actually said. We address this gap with an interview-grounded evaluation framework for personality simulation at a large scale. We extract over 671,000 question-answer pairs from 23,000 verified interview transcripts across 1,000 public personalities, each with an average of 11.5 hours of interview content. We propose a multi-dimensional evaluation framework with four complementary metrics measuring content similarity, factual consistency, personality alignment, and factual knowledge retention. Through systematic comparison, we demonstrate that methods grounded in real interview data substantially outperform those relying solely on biographical profiles or the model's parametric knowledge. We further reveal a trade-off in how interview data is best utilized:...
