Personality assessment improves across video interview types with language models
Cross-Protocol Personality Assessment with LLMs: Aligning Behavioral Evidence with Human Ratings
Artificial Intelligence
Summary
Personality tests based on video interviews usually work only for one specific kind of interview and question set. The authors created a method called CEPA that helps personality assessments work well across different interview styles by linking behaviors from one to another. Their system uses language models and examples rated by humans to better understand the behaviors without needing extra training for each interview type. This approach made personality predictions much more accurate when moving from one interview protocol to another.
What this means in practice
- •For talent acquisition teams: Use CEPA to evaluate job candidates' personalities consistently across different video interview formats without retraining models.
- •For human resources software developers: Integrate CEPA to enable personality scoring modules that work seamlessly for varied interview protocols, improving software flexibility.$Commercial implications: Allows HR software providers to offer cross-protocol personality assessments as a unique feature, enhancing product appeal.
Authors
Wei Shan, Tianyi Zhang, Yuan Zong, Wenming Zheng
Abstract
Personality assessment from asynchronous video interviews (AVIs) plays a crucial role in recruitment by enabling standardized and behaviorally grounded evaluation for job applicants. However, most of the previous works are confined to a single interview protocol. Independently collected protocols differ in question sets and question-trait mapping. Thus, the human-rated evidence from one protocol cannot be used directly under another. To address this limitation, we propose the Cross-protocol Evidence-grounded Personality Assessment (CEPA) framework, which aligns behavioral representations across interview protocols. CEPA addresses protocol heterogeneity by projecting source behavioral records into the target protocol's construct-oriented representation space. It retrieves behaviorally relevant and personality-complementary human-rated exemplars to ground an ensemble of LLM raters, which enables behavior-to-personality associations without target-specific supervision. In cross-protocol experiments, CEPA reduces average mean squared error (MSE) by 43.8% (Forward) and 17.0% (Reverse) relative to the strongest baseline. Our empirical experiments show that human-rated evidence from one protocol can support personality assessment under another without target-specific supervision or retraining.