Scopes of Alignment
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910792758067200 |
|---|---|
| author | Varshney, Kush R. Ashktorab, Zahra Bouneffouf, Djallel Riemer, Matthew Weisz, Justin D. |
| author_facet | Varshney, Kush R. Ashktorab, Zahra Bouneffouf, Djallel Riemer, Matthew Weisz, Justin D. |
| contents | Much of the research focus on AI alignment seeks to align large language models and other foundation models to the context-less and generic values of helpfulness, harmlessness, and honesty. Frontier model providers also strive to align their models with these values. In this paper, we motivate why we need to move beyond such a limited conception and propose three dimensions for doing so. The first scope of alignment is competence: knowledge, skills, or behaviors the model must possess to be useful for its intended purpose. The second scope of alignment is transience: either semantic or episodic depending on the context of use. The third scope of alignment is audience: either mass, public, small-group, or dyadic. At the end of the paper, we use the proposed framework to position some technologies and workflows that go beyond prevailing notions of alignment. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_12405 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Scopes of Alignment Varshney, Kush R. Ashktorab, Zahra Bouneffouf, Djallel Riemer, Matthew Weisz, Justin D. Computers and Society Artificial Intelligence Computation and Language Much of the research focus on AI alignment seeks to align large language models and other foundation models to the context-less and generic values of helpfulness, harmlessness, and honesty. Frontier model providers also strive to align their models with these values. In this paper, we motivate why we need to move beyond such a limited conception and propose three dimensions for doing so. The first scope of alignment is competence: knowledge, skills, or behaviors the model must possess to be useful for its intended purpose. The second scope of alignment is transience: either semantic or episodic depending on the context of use. The third scope of alignment is audience: either mass, public, small-group, or dyadic. At the end of the paper, we use the proposed framework to position some technologies and workflows that go beyond prevailing notions of alignment. |
| title | Scopes of Alignment |
| topic | Computers and Society Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2501.12405 |