Search papers, labs, and topics across Lattice.
Georgia Institute of Technology
3
0
6
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.
LLM agents can now build lasting, reusable "competence" for specific knowledge sources, moving beyond simple retrieval to deep, adaptive understanding.
Simple ensemble methods leveraging rich textual context can outperform state-of-the-art multimodal forecasting approaches on a new benchmark, TimesX, revealing hidden vulnerabilities in existing evaluations.
