Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2512.24149 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915700781613056 |
|---|---|
| author | Song, Changhao Zhang, Yazhou Gao, Hui Yang, Chang Zhang, Peng |
| author_facet | Song, Changhao Zhang, Yazhou Gao, Hui Yang, Chang Zhang, Peng |
| contents | World Models serve as tools for understanding the current state of the world and predicting its future dynamics, with broad application potential across numerous fields. As a key component of world knowledge, emotion significantly influences human decision-making. While existing Large Language Models (LLMs) have shown preliminary capability in capturing world knowledge, they primarily focus on modeling physical-world regularities and lack systematic exploration of emotional factors. In this paper, we first demonstrate the importance of emotion in understanding the world by showing that removing emotionally relevant information degrades reasoning performance. Inspired by theory of mind, we further propose a Large Emotional World Model (LEWM). Specifically, we construct the Emotion-Why-How (EWH) dataset, which integrates emotion into causal relationships and enables reasoning about why actions occur and how emotions drive future world states. Based on this dataset, LEWM explicitly models emotional states alongside visual observations and actions, allowing the world model to predict both future states and emotional transitions. Experimental results show that LEWM more accurately predicts emotion-driven social behaviors while maintaining comparable performance to general world models on basic tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_24149 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Large Emotional World Model Song, Changhao Zhang, Yazhou Gao, Hui Yang, Chang Zhang, Peng Computation and Language World Models serve as tools for understanding the current state of the world and predicting its future dynamics, with broad application potential across numerous fields. As a key component of world knowledge, emotion significantly influences human decision-making. While existing Large Language Models (LLMs) have shown preliminary capability in capturing world knowledge, they primarily focus on modeling physical-world regularities and lack systematic exploration of emotional factors. In this paper, we first demonstrate the importance of emotion in understanding the world by showing that removing emotionally relevant information degrades reasoning performance. Inspired by theory of mind, we further propose a Large Emotional World Model (LEWM). Specifically, we construct the Emotion-Why-How (EWH) dataset, which integrates emotion into causal relationships and enables reasoning about why actions occur and how emotions drive future world states. Based on this dataset, LEWM explicitly models emotional states alongside visual observations and actions, allowing the world model to predict both future states and emotional transitions. Experimental results show that LEWM more accurately predicts emotion-driven social behaviors while maintaining comparable performance to general world models on basic tasks. |
| title | Large Emotional World Model |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2512.24149 |