Natural Language Understanding podcasts

Stanford linguist and computer scientist Chris Manning discusses what linguistics contributed to machine learning and why pragmatics and dialogue remain open problems for language models. The conversation examines early abstraction of verb categories in small transformers, how distributed representations shape learning, and whether language alone can support meaningful representations. It also considers language in world models, diffusion language models, and representation finetuning (ReFT), which steers frozen models through their hidden states. The final discussion asks where knowledge resides and whether concepts occupy linear subspaces.

Hosted by Ravid Shwartz Ziv, Allen Roush

Ellie Pavlick examines what it would mean for a language model to understand words. She compares machine and human language processing, discusses the difficulty of explaining black-box predictions, and considers how studying these differences might clarify both artificial intelligence and human knowledge and creativity.

Hosted by Janna Levin, Steven Strogatz