Model Performance Analysis
Yasaman and Sameer delve into the crucial aspect of considering pre-training data in model performance evaluation. They discuss the limitations of massive language models in learning tasks like two-digit multiplication despite having access to millions of examples. The conversation highlights the importance of understanding biases in foundational models for real-world applications.In this clip
From this podcast

Machine Learning Street Talk (MLST)
#73 - YASAMAN RAZEGHI & Prof. SAMEER SINGH - NLP benchmarks
Related Questions