Knowledge Is Not Static: Order-Aware Hypergraph RAG for Language Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914470839713792 |
|---|---|
| author | Wu, Keshu Kuai, Chenchen Li, Zihao Jiang, Jiwan Shen, Shiyu Wang, Shian Hu, Chan-Wei Tu, Zhengzhong Zhou, Yang |
| author_facet | Wu, Keshu Kuai, Chenchen Li, Zihao Jiang, Jiwan Shen, Shiyu Wang, Shian Hu, Chan-Wei Tu, Zhengzhong Zhou, Yang |
| contents | Retrieval-augmented generation (RAG) enhances large language models by grounding outputs in retrieved knowledge. However, existing RAG methods including graph- and hypergraph-based approaches treat retrieved evidence as an unordered set, implicitly assuming permutation invariance. This assumption is misaligned with many real-world reasoning tasks, where outcomes depend not only on which interactions occur, but also on the order in which they unfold. We propose Order-Aware Knowledge Hypergraph RAG (OKH-RAG), which treats order as a first-class structural property. OKH-RAG represents knowledge as higher-order interactions within a hypergraph augmented with precedence structure, and reformulates retrieval as sequence inference over hyperedges. Instead of selecting independent facts, it recovers coherent interaction trajectories that reflect underlying reasoning processes. A learned transition model infers precedence directly from data without requiring explicit temporal supervision. We evaluate OKH-RAG on order-sensitive question answering and explanation tasks, including tropical cyclone and port operation scenarios. OKH-RAG consistently outperforms permutation-invariant baselines, and ablations show that these gains arise specifically from modeling interaction order. These results highlight a key limitation of set-based retrieval: effective reasoning requires not only retrieving relevant evidence, but organizing it into structured sequences. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_12185 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Knowledge Is Not Static: Order-Aware Hypergraph RAG for Language Models Wu, Keshu Kuai, Chenchen Li, Zihao Jiang, Jiwan Shen, Shiyu Wang, Shian Hu, Chan-Wei Tu, Zhengzhong Zhou, Yang Computation and Language Retrieval-augmented generation (RAG) enhances large language models by grounding outputs in retrieved knowledge. However, existing RAG methods including graph- and hypergraph-based approaches treat retrieved evidence as an unordered set, implicitly assuming permutation invariance. This assumption is misaligned with many real-world reasoning tasks, where outcomes depend not only on which interactions occur, but also on the order in which they unfold. We propose Order-Aware Knowledge Hypergraph RAG (OKH-RAG), which treats order as a first-class structural property. OKH-RAG represents knowledge as higher-order interactions within a hypergraph augmented with precedence structure, and reformulates retrieval as sequence inference over hyperedges. Instead of selecting independent facts, it recovers coherent interaction trajectories that reflect underlying reasoning processes. A learned transition model infers precedence directly from data without requiring explicit temporal supervision. We evaluate OKH-RAG on order-sensitive question answering and explanation tasks, including tropical cyclone and port operation scenarios. OKH-RAG consistently outperforms permutation-invariant baselines, and ablations show that these gains arise specifically from modeling interaction order. These results highlight a key limitation of set-based retrieval: effective reasoning requires not only retrieving relevant evidence, but organizing it into structured sequences. |
| title | Knowledge Is Not Static: Order-Aware Hypergraph RAG for Language Models |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2604.12185 |