Inclusive Artificial Intelligence
Preprint
Abstract
Prevailing methods for assessing and comparing generative AIs incentivize responses that serve a hypothetical representative individual. Evaluating models in these terms presumes homogeneous preferences across the population and engenders selection of agglomerative AIs, which fail to represent the diverse range of interests across individuals. We propose an alternative evaluation method that instead prioritizes inclusive AIs, which provably retain the requisite knowledge not only for subsequent response customization to particular segments of the population but also for utility-maximizing decisions.Keywords
All Related Versions
This publication has 5 references indexed in Scilit:
- In Conversation with Artificial Intelligence: Aligning language Models with Human ValuesPhilosophy & Technology, 2023
- Discovering Language Model Behaviors with Model-Written Evaluations2023
- TruthfulQA: Measuring How Models Mimic Human Falsehoods2022
- Climbing towards NLU: On Meaning, Form, and Understanding in the Age of Data2020
- Guidelines for reinforcement learning in healthcareNature Medicine, 2019