Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2412.10427 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908501355266048 |
|---|---|
| author | Allbert, Rumi Wiles, James K. Grankovsky, Vlad |
| author_facet | Allbert, Rumi Wiles, James K. Grankovsky, Vlad |
| contents | The field of large language models (LLMs) has grown rapidly in recent years, driven by the desire for better efficiency, interpretability, and safe use. Building on the novel approach of "activation engineering," this study explores personality modification in LLMs, drawing inspiration from research like Refusal in LLMs Is Mediated by a Single Direction (arXiv:2406.11717) and Steering Llama 2 via Contrastive Activation Addition (arXiv:2312.06681). We leverage activation engineering to develop a method for identifying and adjusting activation directions related to personality traits, which may allow for dynamic LLM personality fine-tuning. This work aims to further our understanding of LLM interpretability while examining the ethical implications of such developments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_10427 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Identifying and Manipulating Personality Traits in LLMs Through Activation Engineering Allbert, Rumi Wiles, James K. Grankovsky, Vlad Computation and Language Artificial Intelligence The field of large language models (LLMs) has grown rapidly in recent years, driven by the desire for better efficiency, interpretability, and safe use. Building on the novel approach of "activation engineering," this study explores personality modification in LLMs, drawing inspiration from research like Refusal in LLMs Is Mediated by a Single Direction (arXiv:2406.11717) and Steering Llama 2 via Contrastive Activation Addition (arXiv:2312.06681). We leverage activation engineering to develop a method for identifying and adjusting activation directions related to personality traits, which may allow for dynamic LLM personality fine-tuning. This work aims to further our understanding of LLM interpretability while examining the ethical implications of such developments. |
| title | Identifying and Manipulating Personality Traits in LLMs Through Activation Engineering |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2412.10427 |