Search papers, labs, and topics across Lattice.
Yale University
3
0
5
RLMF not only boosts LLMs' ability to accurately express uncertainty but also enhances their self-assessment capabilities, fundamentally reshaping their trustworthiness.
LLMs can't reliably map linguistic uncertainty markers (like "likely" or "possibly") to their own internal confidence levels across different tasks, even when you let them define what those markers mean.
Stop hand-crafting QA datasets for evaluating RAG systems: DoGMaTiQ automates the process with surprisingly high correlation to human judgment, even across languages.
