ISO-RAG: Isoperimetric Noise Control for Retrieval-Augmented Generation
ISO-RAG outperforms state-of-the-art baselines by average absolute gains of 10.0% in retrieval recall and 4.3% in downstream exact match, achieving a superior accuracy-efficiency trade-off by fundamentally eliminating the latency bottleneck of global traversals.
Si-Yuan Zhang, Han-Chen Wang, Dong Wen et al.
· 0 citations