Interactive AI Alignment: Specification, Process, and Evaluation Alignment
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914950305284096 |
|---|---|
| author | Terry, Michael Kulkarni, Chinmay Wattenberg, Martin Dixon, Lucas Morris, Meredith Ringel |
| author_facet | Terry, Michael Kulkarni, Chinmay Wattenberg, Martin Dixon, Lucas Morris, Meredith Ringel |
| contents | Modern AI enables a high-level, declarative form of interaction: Users describe the intended outcome they wish an AI to produce, but do not actually create the outcome themselves. In contrast, in traditional user interfaces, users invoke specific operations to create the desired outcome. This paper revisits the basic input-output interaction cycle in light of this declarative style of interaction, and connects concepts in AI alignment to define three objectives for interactive alignment of AI: specification alignment (aligning on what to do), process alignment (aligning on how to do it), and evaluation alignment (assisting users in verifying and understanding what was produced). Using existing systems as examples, we show how these user-centered views of AI alignment can be used descriptively, prescriptively, and as an evaluative aid. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2311_00710 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Interactive AI Alignment: Specification, Process, and Evaluation Alignment Terry, Michael Kulkarni, Chinmay Wattenberg, Martin Dixon, Lucas Morris, Meredith Ringel Human-Computer Interaction Artificial Intelligence Modern AI enables a high-level, declarative form of interaction: Users describe the intended outcome they wish an AI to produce, but do not actually create the outcome themselves. In contrast, in traditional user interfaces, users invoke specific operations to create the desired outcome. This paper revisits the basic input-output interaction cycle in light of this declarative style of interaction, and connects concepts in AI alignment to define three objectives for interactive alignment of AI: specification alignment (aligning on what to do), process alignment (aligning on how to do it), and evaluation alignment (assisting users in verifying and understanding what was produced). Using existing systems as examples, we show how these user-centered views of AI alignment can be used descriptively, prescriptively, and as an evaluative aid. |
| title | Interactive AI Alignment: Specification, Process, and Evaluation Alignment |
| topic | Human-Computer Interaction Artificial Intelligence |
| url | https://arxiv.org/abs/2311.00710 |