Search papers, labs, and topics across Lattice.
Queen Mary University of London
3
0
4
44
Graph propagation over a temporal knowledge graph can predict clinical advancement with unprecedented accuracy, especially for cases lacking direct evidence.
Fact-checking dialogues? A semantics-aware gate that selectively "de-colloquialises" claims outperforms even LLM-based rewrite approaches, stabilizing downstream verification.
Augmenting claims with retrieved Wikipedia context can boost verifiable claim detection, but the benefit hinges on the domain, model architecture, and learning approach.
