Want to create an interactive transcript for this episode?
Podcast: The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
Episode: Is It Time to Rethink LLM Pre-Training? with Aditi Raghunathan
Description: Today, we're joined by Aditi Raghunathan, assistant professor at Carnegie Mellon University, to discuss the limitations of LLMs and how we can build more adaptable and creative models. We dig into her ICML 2025 Outstanding Paper Award winner, “Roll the dice & look before you leap: Going beyond the creative limits of next-token prediction,” which examines why LLMs struggle with generating truly novel ideas. We dig into the "Roll the dice" approach, which encourages structured exploration by injecting randomness at the start of generation, and the "Look before you leap" concept, which trains models to take "leaps of thought" using alternative obje...