Keep Up With Latest Trending Papers. Computer Science, AI and Machine Learning and more.Subscribe
The Limitations of Generalizable AI Benchmarks
AI and the Everything in the Whole Wide World Benchmark
We explore the limits of a small collection of influential benchmarks in artificial intelligence in order to reveal the construct validity issues inherent in their framing as the functionally"general"broad measures of progress they are set up to be.
Authors
Inioluwa Deborah Raji, Emily M. Bender, Amandalynne Paullada, Emily Denton, Alex Hanna
Read the Paper
Read Paper
◐ Recommended Follows
More
◐ Latest Activity
More