Fuheng Zhao

By embedding online learning directly into LLM call latencies, this framework can cut query costs by nearly 8x, revolutionizing how we optimize semantic data processing.

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.