Language Model Stability
Keith delves into the concept of stability within language models, exploring the interplay between prompts and generated text. By framing language models as systems, he uncovers new research avenues in control theory, shedding light on the controllability of these complex systems.In this clip
From this podcast
Machine Learning Street Talk (MLST)
What’s the Magic Word? A Control Theory of LLM Prompting.
Related Questions