No-regret Language Generation
We introduce no-regret generation, where a generator makes a sublinear number of mistakes uniformly over all demonstration sequences and compatible target languages, and extend …
On Generation in Metric Spaces
Characterizes generation in metric spaces using a scale-sensitive closure dimension, showing how geometry governs the stability of generation across novelty scales.
Generation through the lens of learning theory
We study generation in statistical learning theory and characterize when a hypothesis class supports uniform, non-uniform, or prompted generation. These characterizations use a new …