Philosophy-informed Machine Learning
This is an incremental proposal for improving ML models by incorporating philosophical ideas, targeting researchers and practitioners interested in ethical and conceptual alignment in AI.
The paper introduces Philosophy-informed Machine Learning (PhIML) as an approach that integrates analytic philosophy into ML models and processes, aiming to enhance capabilities and alignment with philosophical concepts, but it does not report specific experimental results or concrete numbers.
Philosophy-informed machine learning (PhIML) directly infuses core ideas from analytic philosophy into ML model architectures, objectives, and evaluation protocols. Therefore, PhIML promises new capabilities through models that respect philosophical concepts and values by design. From this lens, this paper reviews conceptual foundations to demonstrate philosophical gains and alignment. In addition, we present case studies on how ML users/designers can adopt PhIML as an agnostic post-hoc tool or intrinsically build it into ML model architectures. Finally, this paper sheds light on open technical barriers alongside philosophical, practical, and governance challenges and outlines a research roadmap toward safe, philosophy-aware, and ethically responsible PhIML.