ValueMap: Mapping Crowdsourced Human Values to Computational Scores for Bi-directional Alignment

Priya Ronald DCosta, Rupkatha Hira

Keywords: Human-AI alignment, ValueMap, computational proxies, crowdsourced values, ethical AI, bi-directional alignment, social justice, fairness, communication values, cooperation, interdisciplinary AI ethics, value-sensitive design, AI evaluation metrics, human values operationalization

TL;DR: ValueMap is a crowdsourced framework that maps human values to computational proxies, enabling adaptive and measurable bi-directional human-AI alignment.

Abstract: Defining values for bi-directional alignment is challenging due to their dynamic nature. Traditional surveys are often biased, necessitating a shift to objective computational methods. We propose ValueMap, a framework mapping values from literature to computational proxies, enabling AI systems to adapt to evolving human values.

Submission Type: Tiny Paper (2 Pages)

Archival Option: This is a non-archival submission

Presentation Venue Preference: ICLR 2025

Submission Number: 85