ValueMap: Mapping Crowdsourced Human Values to Computational Scores for Bi-Directional 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.
Cite
Text
DCosta and Hira. "ValueMap: Mapping Crowdsourced Human Values to Computational Scores for Bi-Directional Alignment." ICLR 2025 Workshops: Bi-Align, 2025.Markdown
[DCosta and Hira. "ValueMap: Mapping Crowdsourced Human Values to Computational Scores for Bi-Directional Alignment." ICLR 2025 Workshops: Bi-Align, 2025.](https://mlanthology.org/iclrw/2025/dcosta2025iclrw-valuemap/)BibTeX
@inproceedings{dcosta2025iclrw-valuemap,
title = {{ValueMap: Mapping Crowdsourced Human Values to Computational Scores for Bi-Directional Alignment}},
author = {DCosta, Priya Ronald and Hira, Rupkatha},
booktitle = {ICLR 2025 Workshops: Bi-Align},
year = {2025},
url = {https://mlanthology.org/iclrw/2025/dcosta2025iclrw-valuemap/}
}