[Paper] Modeling Complex Behaviors: Multi-Personality Composition and Dynamic Switching in Vision-Language Models

Source: arXiv - 2606.11074v1

Overview

With the widespread deployment of Multimodal Large Language Models (MLLMs) in social interaction, understanding and controlling their behavior under complex personality conditions is essential. This paper introduces explicit personality conditioning and establishes a systematic evaluation framework encompassing single-personality induction, multi-personality induction, and personality switching. Experiments show that personality induction improves image captioning performance but can impair performance on tasks requiring precise reasoning, such as visual question answering (VQA). Balancing and residual effects are observed during multi-trait composition and dynamic switching, indicating that model behavior is co-modulated by both previous and current personality constraints. Existing prompt-based personality induction methods show limited transferability to multimodal settings. Our work reveals the dynamic and complex nature of personality modeling in MLLMs and underscores the need for robust, tailored methods for personality induction and evaluation. The code will be released when the paper is accepted.

Key Contributions

This paper presents research in the following areas:

• cs.CL
• cs.AI

Methodology

Please refer to the full paper for detailed methodology.

Practical Implications

This research contributes to the advancement of cs.CL.

Authors

• Peiqi Jia
• Haonan Jia
• Ziqi Miao
• Linkang Du
• Yuntao Wang
• Zhou Su

Paper Information

• arXiv ID: 2606.11074v1
• Categories: cs.CL, cs.AI
• Published: June 9, 2026
• PDF: Download PDF