Recommended Citation
Rachel Hong, Yael Eiger, Jevan A. Hutson, Os Keyes & William Agnew, Slurry-as-a-Service: A Modest Proposal on Scalable Pluralistic Alignment for Nutrient Optimization, Proceedings of the Extended Abstracts of the 2026 CHI Conference on Human Factors in Computing Systems (CHI EA '26) (2026).
Publication Title
Proceedings of the Extended Abstracts of the 2026 CHI Conference on Human Factors in Computing Systems (CHI EA '26)
Keywords
Pluralistic Alignment, Values-as-Configuration, Constitutional AI, Preference Learning, Personalization, AI Safety, AI Ethics
Document Type
Article
Abstract
Pluralistic alignment has emerged as a promising approach for ensuring that large language models (LLMs) faithfully represent the diversity, nuance, and conflict inherent in human values. In this work, we study a high-stakes deployment context—mulching—where automated systems transform selected individuals into nutrientrich slurry for the dual purposes of food security and aesthetic population management. Building on recent pluralistic alignment frameworks, we introduce ValueMulch™, a reproducible training, deployment, and certification pipeline for aligning mulching models (MMs) to a wide range of community norms. Through a real-world testbed spanning 32 communities, we show that ValueMulch™ improves distributional agreement with community mulching preferences relative to frontier baselines. We conclude with a discussion of ethical considerations, limitations, and implications for researchers seeking to align systems to the full spectrum of human values—especially when those values are inconsistent, commercially inconvenient, or nutritionally underutilized.