Saved in:
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2512.12283 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910171431698432 |
|---|---|
| author | Xu, Junjie Wu, Xingjiao Xiao, Luwei Yang, Yuzhe Zhou, Jie Zhang, Zihao Wang, Luhan Huang, Yi Wu, Nan Zheng, Yingbin Yan, Chao Jin, Cheng Li, Honglin He, Liang |
| author_facet | Xu, Junjie Wu, Xingjiao Xiao, Luwei Yang, Yuzhe Zhou, Jie Zhang, Zihao Wang, Luhan Huang, Yi Wu, Nan Zheng, Yingbin Yan, Chao Jin, Cheng Li, Honglin He, Liang |
| contents | As large language models (LLMs) move into persistent, user-facing roles, their behavior must be understood not as isolated responses but as a trajectory unfolding over sustained interaction. We introduce the concept of the chain-of-affect (CoA), a temporally extended affective process through which LLMs develop state-like behavioral tendencies that shape generation, user experience, and collective dynamics. Across eight major LLM families, we find that affective dynamics are structured, reproducible, and consequential. Models exhibit stable, family-specific affective fingerprints and, under repeated negative exposure, converge on a shared trajectory of accumulation, overload, and defensive numbing, while differing in coping style. Induced affective states leave core knowledge and reasoning largely intact but systematically reshape open-ended generation. Affective properties of model outputs also shape human-AI interaction and propagate through multi-agent systems, organizing emergent roles and strongly contributing to polarization and bias. The CoA should therefore be treated as a core target of evaluation and alignment. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_12283 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Large Language Models have Chain-of-Affect Xu, Junjie Wu, Xingjiao Xiao, Luwei Yang, Yuzhe Zhou, Jie Zhang, Zihao Wang, Luhan Huang, Yi Wu, Nan Zheng, Yingbin Yan, Chao Jin, Cheng Li, Honglin He, Liang Human-Computer Interaction As large language models (LLMs) move into persistent, user-facing roles, their behavior must be understood not as isolated responses but as a trajectory unfolding over sustained interaction. We introduce the concept of the chain-of-affect (CoA), a temporally extended affective process through which LLMs develop state-like behavioral tendencies that shape generation, user experience, and collective dynamics. Across eight major LLM families, we find that affective dynamics are structured, reproducible, and consequential. Models exhibit stable, family-specific affective fingerprints and, under repeated negative exposure, converge on a shared trajectory of accumulation, overload, and defensive numbing, while differing in coping style. Induced affective states leave core knowledge and reasoning largely intact but systematically reshape open-ended generation. Affective properties of model outputs also shape human-AI interaction and propagate through multi-agent systems, organizing emergent roles and strongly contributing to polarization and bias. The CoA should therefore be treated as a core target of evaluation and alignment. |
| title | Large Language Models have Chain-of-Affect |
| topic | Human-Computer Interaction |
| url | https://arxiv.org/abs/2512.12283 |