Track synthesis, materials and catalysis as it is published.
Search papers, labs, and topics across Lattice.
Affiliation:
2
0
4
LLMs can be steered to generate diverse, relevant responses by explicitly searching for unoccupied semantic "gaps" in their output space, reducing output collision by over 10%.
Prompt optimization methods that iteratively rewrite prompts with LLM feedback often overfit to training data, but a new regularization framework achieves up to +16.5% OOD generalization gains by controlling prompt representation.