Exploring the Personality Traits of LLMs through Latent Features Steering
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910829729808384 |
|---|---|
| author | Yang, Shu Zhu, Shenzhe Liu, Liang Hu, Lijie Li, Mengdi Wang, Di |
| author_facet | Yang, Shu Zhu, Shenzhe Liu, Liang Hu, Lijie Li, Mengdi Wang, Di |
| contents | Large language models (LLMs) have significantly advanced dialogue systems and role-playing agents through their ability to generate human-like text. While prior studies have shown that LLMs can exhibit distinct and consistent personalities, the mechanisms through which these models encode and express specific personality traits remain poorly understood. To address this, we investigate how various factors, such as cultural norms and environmental stressors, encoded within LLMs, shape their personality traits, guided by the theoretical framework of social determinism. Inspired by related work on LLM interpretability, we propose a training-free approach to modify the model's behavior by extracting and steering latent features corresponding to factors within the model, thereby eliminating the need for retraining. Furthermore, we analyze the implications of these factors for model safety, focusing on their impact through the lens of personality. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_10863 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Exploring the Personality Traits of LLMs through Latent Features Steering Yang, Shu Zhu, Shenzhe Liu, Liang Hu, Lijie Li, Mengdi Wang, Di Computation and Language Artificial Intelligence Large language models (LLMs) have significantly advanced dialogue systems and role-playing agents through their ability to generate human-like text. While prior studies have shown that LLMs can exhibit distinct and consistent personalities, the mechanisms through which these models encode and express specific personality traits remain poorly understood. To address this, we investigate how various factors, such as cultural norms and environmental stressors, encoded within LLMs, shape their personality traits, guided by the theoretical framework of social determinism. Inspired by related work on LLM interpretability, we propose a training-free approach to modify the model's behavior by extracting and steering latent features corresponding to factors within the model, thereby eliminating the need for retraining. Furthermore, we analyze the implications of these factors for model safety, focusing on their impact through the lens of personality. |
| title | Exploring the Personality Traits of LLMs through Latent Features Steering |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2410.10863 |