A Method for Learning Value Systems in Generative AI

arXiv:2607.16903v1 Announce Type: cross Abstract: Value-aware AI systems require explicit computational representations of human values (groundings) and their aggregation into value systems in order to align their decisions with ours. As such representations are difficult to elicit, value learning seeks to infer them by observing human behaviour. This work addresses the lack of grounded value learning methods in generative AI: existing approaches typically replicate human preferences without awareness of the multidimensional structure of value alignment, or lack principled value system elicitation methods. To address these gaps, we adapt a previously validated value system learning method to the generative AI setting, which, based on pairwise prompt-response preference data, simultaneously learns: i) an implementation of a grounding for a set of values given by a multi-objective reward model, and ii) a value system representation in the form of a weighted linear scalarization of the previous grounding model. To ensure that the learned value systems are based on coherent value representations, our algorithm dynamically prioritizes the grounding learning process. We evaluate the method against baselines and a contemporary method on prompt-response preference datasets. Results show competitive performance and minimal trade-offs against the baselines, while improving explainability.

Abstract:Value-aware AI systems require explicit computational representations of human values (groundings) and their aggregation into value systems in order to align their decisions with ours. As such representations are difficult to elicit, value learning seeks to infer them by observing human behaviour. This work addresses the lack of grounded value learning methods in generative AI: existing approaches typically replicate human preferences without awareness of the multidimensional structure of value alignment, or lack principled value system elicitation methods. To address these gaps, we adapt a previously validated value system learning method to the generative AI setting, which, based on pairwise prompt-response preference data, simultaneously learns: i) an implementation of a grounding for a set of values given by a multi-objective reward model, and ii) a value system representation in the form of a weighted linear scalarization of the previous grounding model. To ensure that the learned value systems are based on coherent value representations, our algorithm dynamically prioritizes the grounding learning process. We evaluate the method against baselines and a contemporary method on prompt-response preference datasets. Results show competitive performance and minimal trade-offs against the baselines, while improving explainability.

Full version of a to be published paper in proceedings of the 9th AAAI/ACM conference in AI, Ethics and Society (AIES 2026). Includes supplementary material. 20 pages, 2 figures

Computers and Society (cs.CY); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG)

I.2.7; I.2.6; J.4; K.4.0

arXiv:2607.16903 [cs.CY]

(or arXiv:2607.16903v1 [cs.CY] for this version)

https://doi.org/10.48550/arXiv.2607.16903 arXiv-issued DOI via DataCite (pending registration)

analiza aiqbench

A Method for Learning Value Systems in Generative AI

Subiecte conexe