Cross-Protocol Personality Assessment with LLMs: Aligning Behavioral Evidence with Human Ratings
The empirical experiments show that human-rated evidence from one protocol can support personality assessment under another without target-specific supervision or retraining, and the Cross-protocol Evidence-grounded Personality Assessment framework is proposed, which aligns behavioral representations across interview p...
Shan Wei, Tian-Yi Zhang, Yuan Zong et al.
· 0 citations