arXiv cs.AI· Wei Shan, Tianyi Zhang, Yuan Zong, Wenming Zheng·· 3 天前AI 评分23
用 LLM 做跨协议人格评估：CEPA 框架让行为证据与人工评分对齐
Cross-Protocol Personality Assessment with LLMs: Aligning Behavioral Evidence with Human Ratings
AI 导读
针对异步视频面试（AVI）中不同面试协议问题集与题目-特质映射不一致、人工评分证据无法跨协议复用的问题，研究者提出 CEPA 框架，将源协议行为记录投影到目标协议的构念导向表示空间，并检索行为相关且人格互补的人工评分样例来支撑 LLM 评分器集成，无需目标协议监督。
正文 · 原文
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.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.16050 [cs.AI] |
| (or arXiv:2610.16050v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.16050 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Wei Shan [view email]
[v1]
Mon, 12 Oct 2026 01:44:38 UTC (485 KB)
来源：arXiv cs.AI · arxiv.org