Showing cs.IRShow all
2 papers · 1 filter
cs.IR2026
MVR-cache: Optimizing Semantic Caching via Multi-Vector Retrieval and Learned Prompt Segmentation
Ali Noshad, Zishan Zheng, Yinjun Wu
To reduce LLM costs and latency, semantic caching systems must accurately identify when a new prompt matches a cached one. Current methods often rely on simplistic similarity measu…
cs.IR2025
POQD: Performance-Oriented Query Decomposer for Multi-vector retrieval
Yaoyang Liu, Junlin Li, Yinjun Wu +1
Although Multi-Vector Retrieval (MVR) has achieved the state of the art on many information retrieval (IR) tasks, its performance highly depends on how to decompose queries into sm…