Language-Specific Representation of Emotion-Concept Knowledge Causally Supports Emotion Inference
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910701197459456 |
|---|---|
| author | Li, Ming Su, Yusheng Huang, Hsiu-Yuan Cheng, Jiali Hu, Xin Zhang, Xinmiao Wang, Huadong Qin, Yujia Wang, Xiaozhi Lindquist, Kristen A. Liu, Zhiyuan Zhang, Dan |
| author_facet | Li, Ming Su, Yusheng Huang, Hsiu-Yuan Cheng, Jiali Hu, Xin Zhang, Xinmiao Wang, Huadong Qin, Yujia Wang, Xiaozhi Lindquist, Kristen A. Liu, Zhiyuan Zhang, Dan |
| contents | Humans no doubt use language to communicate about their emotional experiences, but does language in turn help humans understand emotions, or is language just a vehicle of communication? This study used a form of artificial intelligence (AI) known as large language models (LLMs) to assess whether language-based representations of emotion causally contribute to the AI's ability to generate inferences about the emotional meaning of novel situations. Fourteen attributes of human emotion concept representation were found to be represented by the LLM's distinct artificial neuron populations. By manipulating these attribute-related neurons, we in turn demonstrated the role of emotion concept knowledge in generative emotion inference. The attribute-specific performance deterioration was related to the importance of different attributes in human mental space. Our findings provide a proof-in-concept that even a LLM can learn about emotions in the absence of sensory-motor representations and highlight the contribution of language-derived emotion-concept knowledge for emotion inference. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2302_09582 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Language-Specific Representation of Emotion-Concept Knowledge Causally Supports Emotion Inference Li, Ming Su, Yusheng Huang, Hsiu-Yuan Cheng, Jiali Hu, Xin Zhang, Xinmiao Wang, Huadong Qin, Yujia Wang, Xiaozhi Lindquist, Kristen A. Liu, Zhiyuan Zhang, Dan Artificial Intelligence Computation and Language Humans no doubt use language to communicate about their emotional experiences, but does language in turn help humans understand emotions, or is language just a vehicle of communication? This study used a form of artificial intelligence (AI) known as large language models (LLMs) to assess whether language-based representations of emotion causally contribute to the AI's ability to generate inferences about the emotional meaning of novel situations. Fourteen attributes of human emotion concept representation were found to be represented by the LLM's distinct artificial neuron populations. By manipulating these attribute-related neurons, we in turn demonstrated the role of emotion concept knowledge in generative emotion inference. The attribute-specific performance deterioration was related to the importance of different attributes in human mental space. Our findings provide a proof-in-concept that even a LLM can learn about emotions in the absence of sensory-motor representations and highlight the contribution of language-derived emotion-concept knowledge for emotion inference. |
| title | Language-Specific Representation of Emotion-Concept Knowledge Causally Supports Emotion Inference |
| topic | Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2302.09582 |