Search papers, labs, and topics across Lattice.
UC Santa Barbara
3
0
5
8
Schema retrieval can be effectively optimized with lightweight, corpus-adaptive fine-tuning, achieving performance on par with much larger models.
Flipping relevance labels via LLM-generated complementary instructions boosts instruction-following retrieval by 45%, proving that targeted data synthesis beats brute-force scaling.
Code-switching can degrade information retrieval performance by up to 27%, revealing a critical blind spot in current multilingual models.
