Search papers, labs, and topics across Lattice.
Affiliation:
3
0
5
LLMs can learn to generate syntactically valid text without sacrificing semantic quality, even with underspecified prompts, by leveraging self-supervised rewards derived from their own likelihoods.
Nonsensical inputs can infiltrate LLM-generated knowledge graphs, but DARKSIDE offers a novel method to track and mitigate these risks effectively.
OntoExtend enables precise ontology enrichment by directly aligning extensions with emerging requirements, significantly reducing the need for extensive manual revisions.
