Metraipolis › archive › dc_ab0e83d284a2
ISO-RAG: Isoperimetric Noise Control for Retrieval-Augmented Generation — arXiv:2609.00513
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.00513
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T06:31:56.170Z
- SHA-256 of the archived text
50a0f2cbb82bdfe93c3f34237332e50ac2c32f66c4da1de359aa4d6f8f94c89b- Stable URL of this page
https://metraipolis.com/documento/dc_ab0e83d284a2
How to cite
ISO-RAG: Isoperimetric Noise Control for Retrieval-Augmented Generation — arXiv:2609.00513 — arXiv (en), https://arxiv.org/abs/2609.00513 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ab0e83d284a2 (Metraipolis archive dc_ab0e83d284a2, sha256 50a0f2cbb82bdfe93c3f34237332e50ac2c32f66c4da1de359aa4d6f8f94c89b)
BibTeX
@misc{dcab0e83d284a2,
title = {ISO-RAG: Isoperimetric Noise Control for Retrieval-Augmented Generation — arXiv:2609.00513},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.00513},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ab0e83d284a2; sha256 50a0f2cbb82bdfe93c3f34237332e50ac2c32f66c4da1de359aa4d6f8f94c89b},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.00513. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Retrieval-Augmented Generation (RAG) mitigates large language models (LLMs) hallucinations, yet conventional dense retrieval struggles with the complex reasoning paths of multi-hop question answering (QA). Graph-based RAG captures multi-step relationships but suffers from severe semantic drift and high online latency due to noisy global graph traversals. Thus, we propose ISO-RAG (ISOperimetric Retrieval-Augmented Generation), a geometry-aware RAG framework. By projecting the underlying knowledge graph into a hyperbolic Poincare ball to precompute node-wise isoperimetric profiles, ISO-RAG prunes spurious edges during retrieval, restricting the search space to a strictly localized subgraph. This topological purification regulates Personalized PageRank (PPR) diffusion driving the retrieval process, ensuring exact and low-latency convergence. Experiments on multi-hop QA benchmarks demonstrate that 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. Our source code is available at this https URL . Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-02 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.00513 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-17T06:15:12.614Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).