Traits Run Deeper: Trait-Specific Asymmetric Fusion for Personality Assessment

特质深层挖掘：用于人格评估的特质特定非对称融合

Abstract: Personality assessment aims to infer stable personality traits from dynamic behaviors across language, voice, and facial cues. Since different personality dimensions are revealed through distinct behavioral perspectives, modeling trait-specific evidence is challenging. However, most existing approaches adopt a uniform multimodal fusion strategy across all dimensions, assuming identical modality contributions. This overlooks trait-specific modality preferences and introduces cross-modal interference.

摘要： 人格评估旨在通过语言、语音和面部线索等动态行为来推断稳定的人格特质。由于不同的人格维度通过不同的行为视角展现，因此对特质特定的证据进行建模极具挑战性。然而，大多数现有方法在所有维度上采用统一的多模态融合策略，假设各模态的贡献相同。这忽略了特质特定的模态偏好，并引入了跨模态干扰。

To address this issue, we propose a novel personality assessment framework called Traits Run Deeper, which consists of three components. Specifically, the Multimodal Foundation Representation (MFR) module constructs personality-oriented multimodal inputs and leverages psychology-informed semantic templates as anchors, enabling foundation models to capture trait-relevant information.

为了解决这一问题，我们提出了一种名为“Traits Run Deeper”的新型人格评估框架，该框架由三个部分组成。具体而言，多模态基础表示（MFR）模块构建了面向人格的多模态输入，并利用心理学启发的语义模板作为锚点，使基础模型能够捕捉与特质相关的信息。

Building upon MFR, the Trait-Specific Modality Fusion (TSMF) module acts as an asymmetric fusion mechanism, allowing each dimension to selectively exploit different modality pathways from modality-specific modeling to complementary fusion. Thus, TSMF captures heterogeneous modality preferences while reducing cross-modal contamination.

在 MFR 的基础上，特质特定模态融合（TSMF）模块充当了一种非对称融合机制，允许每个维度从模态特定建模到互补融合，选择性地利用不同的模态路径。因此，TSMF 在捕捉异构模态偏好的同时，减少了跨模态污染。

Furthermore, the Distribution-Calibrated Personality Regression (DCPR) module mitigates label imbalance and central tendency bias through target distribution calibration, improving robustness and stability. Experimental results on the AVI Challenge 2026 validation set demonstrate the effectiveness of the proposed framework, reducing mean squared error (MSE) by approximately 25% compared with the baseline. Consistent improvements are observed on the official test set, where our method achieves the best performance and ranks first in the Personality Assessment Track. The source code will be made available at this https URL.

此外，分布校准人格回归（DCPR）模块通过目标分布校准减轻了标签不平衡和中心趋势偏差，提高了鲁棒性和稳定性。在 AVI Challenge 2026 验证集上的实验结果证明了该框架的有效性，与基线相比，均方误差（MSE）降低了约 25%。在官方测试集上也观察到了持续的改进，我们的方法取得了最佳性能，并在人格评估赛道中排名第一。源代码将在该链接提供。