Scopes of Alignment
This work addresses the need for more nuanced AI alignment strategies for researchers and developers, but it is incremental as it builds on existing concepts without introducing new methods or data.
The paper tackles the problem of AI alignment being too narrowly focused on generic values like helpfulness and harmlessness, proposing a framework with three dimensions—competence, transience, and audience—to broaden alignment approaches.
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.