InterviewSim: A Scalable Framework for Interview-Grounded Personality Simulation

TL;DR

This paper introduces InterviewSim, a large-scale interview-grounded evaluation framework for personality simulation using extensive real interview data, enabling better assessment of personality models' authenticity and factual accuracy.

Contribution

It presents a novel large-scale dataset and multi-dimensional evaluation framework for assessing personality simulation grounded in real interview data, surpassing prior proxy-based methods.

Findings

Models grounded in real interview data outperform profile-based approaches.

Retrieval-augmented methods excel at capturing personality style.

Chronological methods better preserve factual knowledge.

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: retrieval-augmented methods excel at capturing personality style and response quality, while chronological-based methods better preserve factual consistency and knowledge retention. Our evaluation framework enables principled method selection based on application requirements, and our empirical findings provide actionable insights for advancing personality simulation research.