With coauthors from HLS and OpenAI, Manon Revel introduces evaluative metrics for reward models' alignment with values expressed in training datasets. "The importance of having a high-quality ...

For several years, “alignment” has been headlined as the key to fixing our broken healthcare experience, transforming the outcomes and economics of benefits programs. Self-insured employers have been ...

As artificial intelligence (AI) systems increasingly support value-laden decisions, users may judge whether an advisor’s observable choices align with their own priorities. Prior theories of value ...