Metraipolis › archive › dc_79b80d4dca24
CAGE: Coherence-Aware Graph Encoding for Retrieval-Augmented Generation — arXiv:2609.04647
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.04647
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T22:35:00.188Z
- SHA-256 of the archived text
e14316c48c9d2a18cdec92d96c6de354eeb9b8fa689ce3fa9c4e9808a7def740- Stable URL of this page
https://metraipolis.com/documento/dc_79b80d4dca24
How to cite
CAGE: Coherence-Aware Graph Encoding for Retrieval-Augmented Generation — arXiv:2609.04647 — arXiv (en), https://arxiv.org/abs/2609.04647 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_79b80d4dca24 (Metraipolis archive dc_79b80d4dca24, sha256 e14316c48c9d2a18cdec92d96c6de354eeb9b8fa689ce3fa9c4e9808a7def740)
BibTeX
@misc{dc79b80d4dca24,
title = {CAGE: Coherence-Aware Graph Encoding for Retrieval-Augmented Generation — arXiv:2609.04647},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.04647},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_79b80d4dca24; sha256 e14316c48c9d2a18cdec92d96c6de354eeb9b8fa689ce3fa9c4e9808a7def740},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.04647. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Traditional Retrieval-Augmented Generation (RAG) systems score each passage independently against the query, assembling context sets that may be individually relevant yet collectively incoherent. We introduce Coherence-Aware Graph Encoding (CAGE), a reranking framework that models "between-chunk coherence" across four dimensions: Intra-Domain Relevance, Noise Resistance, Informational Bonding, and Factual Consistency. Our pipeline transforms retrieved passages into directed heterogeneous entity graphs, amplifies factual anchors via min-out-degree reweighting, encodes structural patterns through a Relational Graph Convolutional Network, and fuses inter-chunk coherence with query relevance for final ranking. Evaluated across four multi-hop benchmarks, CAGE matches or outperforms strong baselines including monoT5 in Recall@5 on bridge-dominated datasets and consistently improves downstream Exact Match, demonstrating that structurally coherent context yields more precise answers even when retrieval recall is comparable or lower. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-07 in cs.CL). Categorie arXiv: Computation and Language (cs.CL) ; Information Retrieval (cs.IR). Pagina del lavoro: https://arxiv.org/abs/2609.04647 — 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 2026-10-16T22:21:16.273Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).