English(EN) Modeling Complex Behaviors: Multi-Personality Composition and Dynamic Switching in Vision-Language Models

新框架模拟多模态大语言模型中的复杂人格

作者 PulseAugur 编辑部 · [2 个来源] · 2026-06-09 16:34

研究人员开发了一个新的框架，用于条件化和评估多模态大语言模型（MLLMs）的人格。他们的实验表明，虽然人格诱导可以增强图像字幕生成，但可能会阻碍视觉问答等精确推理任务的性能。研究还观察到多重特征构成和动态切换过程中的平衡和残余效应，这表明模型行为受到过去和现在人格约束的影响。 AI

影响引入了一个用于控制和评估MLLM人格的框架，有可能提高其社交互动能力。

排序理由该集群包含一篇学术论文，详细介绍了一种用于建模和评估视觉语言模型中复杂行为的新方法。

AI 生成摘要 · Google Gemini · 来自 2 个来源。我们如何撰写摘要 →

报道来源 [2]

arXiv cs.AI TIER_1 English(EN) · Peiqi Jia (Xi'an Jiaotong University), Haonan Jia (Beihang University), Ziqi Miao (Beihang University), Linkang Du (Xi'an Jiaotong University), Yuntao Wang (Xi'an Jiaotong University), Zhou Su (Xi'an Jiaotong University) · 2026-06-10 04:00

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

arXiv:2606.11074v1 Announce Type: cross Abstract: 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 perso…
arXiv cs.CL TIER_1 English(EN) · Zhou Su · 2026-06-09 16:34

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

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 e…