Search papers, labs, and topics across Lattice.
The University of Queensland
3
0
4
Long-context LLMs can drastically reduce the number of model calls needed for passage re-ranking, achieving efficiency without sacrificing effectiveness.
Forget fancy LLM-guided chunking for standard information retrieval – simple, structure-based methods still reign supreme.
Encoder-decoder LLMs exhibit surprisingly strong inherent resilience to jailbreak prompt injection attacks when used as rankers, challenging the assumption that all LLMs are equally vulnerable.
