Meera Desai
@madesai.bsky.social
PhD student at University of Michigan School of Information. Data and evaluation practices for language models / language models as cultural technologies.
https://meera-desai.com
https://meera-desai.com
Reposted by Meera Desai
Evaluating Generative AI Systems is a Social Science Measurement Challenge: arxiv.org/abs/2411.10939
TL;DR: The ML community would benefit from learning from and drawing on the social sciences when evaluating GenAI systems.
TL;DR: The ML community would benefit from learning from and drawing on the social sciences when evaluating GenAI systems.
December 2, 2024 at 11:02 PM
Evaluating Generative AI Systems is a Social Science Measurement Challenge: arxiv.org/abs/2411.10939
TL;DR: The ML community would benefit from learning from and drawing on the social sciences when evaluating GenAI systems.
TL;DR: The ML community would benefit from learning from and drawing on the social sciences when evaluating GenAI systems.