# Debiased Multimodal Personality Understanding through Dual Causal Intervention

arXiv: https://arxiv.org/abs/2605.06371 · HTML: https://mlsanity.com/paper/2605.06371/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 54 references that are in the map.
- First posted on arXiv 7 May 2026.

## Builds on (most cited first, 16 of 16)

- [VideoMamba: State Space Model for Efficient Video Understanding](https://mlsanity.com/paper/2403.06977/) (2024)
- [Graph Neural Networks for Graphs with Heterophily: A Survey](https://mlsanity.com/paper/2202.07082/) (2022)
- [AI Agents Under Threat: A Survey of Key Security Challenges and Future Pathways](https://mlsanity.com/paper/2406.02630/) (2024)
- [Causal Attention for Vision-Language Tasks](https://mlsanity.com/paper/2103.03493/) (2021)
- [Cobra: Extending Mamba to Multi-Modal Large Language Model for Efficient Inference](https://mlsanity.com/paper/2403.14520/) (2024)
- [Multimodal Sentiment Analysis with Word-Level Fusion and Reinforcement Learning](https://mlsanity.com/paper/1802.00924/) (2018)
- [MDD-5k: A New Diagnostic Conversation Dataset for Mental Disorders Synthesized via Neuro-Symbolic LLM Agents](https://mlsanity.com/paper/2408.12142/) (2024)
- [Deep Impression: Audiovisual Deep Residual Networks for Multimodal Apparent Personality Trait Recognition](https://mlsanity.com/paper/1609.05119/) (2016)
- [Bi-modal First Impressions Recognition using Temporally Ordered Deep Audio and Stochastic Visual Features](https://mlsanity.com/paper/1610.10048/) (2016)
- [An Open-source Benchmark of Deep Learning Models for Audio-visual Apparent and Self-reported Personality Recognition](https://mlsanity.com/paper/2210.09138/) (2022)
- [Deep Causal Learning: Representation, Discovery and Inference](https://mlsanity.com/paper/2211.03374/) (2022)
- [MDPE: A Multimodal Deception Dataset with Personality and Emotional Characteristics](https://mlsanity.com/paper/2407.12274/) (2024)
- [Predicting User Behavior in Smart Spaces with LLM-Enhanced Logs and Personalized Prompts](https://mlsanity.com/paper/2412.12653/) (2024)
- [Pose as a Modality: A Psychology-Inspired Network for Personality Recognition with a New Multimodal Dataset](https://mlsanity.com/paper/2503.12912/) (2025)
- [Deconfounded Reasoning for Multimodal Fake News Detection via Causal Intervention](https://mlsanity.com/paper/2504.09163/) (2025)
- [RecruitView: A Multimodal Dataset for Predicting Personality and Interview Performance for Human Resources Applications](https://mlsanity.com/paper/2512.00450/) (2025)

## Abstract (arXiv)

Multimodalpersonalityunderstandingplaysacriticalroleinhuman centered artificial intelligence. Previous work mainly focus on learn-ing rich multimodal representations for video personality under standing. However, they often suffer from potential harm caused by subject bias (e.g., observable age and unobservable mental states), as subjects originate from diverse demographic backgrounds. Learn ing such spurious associations between multimodal features and traits may lead to unfair personality understanding. In this work, weconstruct aStructural Causal Model (SCM)toanalyze theimpact of these biases from a causal perspective, and propose a novel Dual Causal Adjustment Network (DCAN) to mitigate the interference of subject attributes on personality understanding. Specifically, we design a Back-door Adjustment Causal Learning (BACL) module to block spurious correlations from observable demographic factors via a prototype-based confounder dictionary, and subsequently ap ply a Front-door Adjustment Causal Learning (FACL) module to ad dress latent and unobservable biases throughalearnedmediatordic tionary intervention, thereby achieving causal disentanglement of representations for deconfounded reasoning. Importantly, we con struct a Demographic-annotated Multimodal Student Personality (DMSP) dataset to support the analysis and discussion of fairness related factors. Extensive experiments on the benchmark dataset CFI-V2 and our DMSPdataset demonstrate that DCAN consistently improves prediction accuracy, reaching 92.11% and 92.90%, respec tively. Meanwhile, the improvementsinthefairnessmetricsofequal opportunity and demographic parity are 6.57% and 7.97% on CFI-V2, and 15.38% and 20.06% on the DMSP dataset. Our code and DMSP dataset are available at https://github.com/Sabrina-han/DCAN