Beyond Benchmarks
Emily discusses the limitations of traditional benchmarks and introduces complementary methods like test suites and auditing to better assess system performance. She emphasizes the importance of understanding failure modes through adversarial testing and error analysis, advocating for a more nuanced approach to evaluating machine learning systems.In this clip
From this podcast
Gradient Dissent - A Machine Learning Podcast
Emily M. Bender — Language Models and Linguistics
Related Questions