arXiv cs.AI· Zafer Sahinoglu, Abdulazeez Mohammed, Buse Yaren Kazangirler, Cahit Berkay Kazangirler·· 13 小时前AI 评分31
SpectRAG：面向多跳 RAG 的加权块图谱与 Token 预算上下文选择
SpectRAG: Weighted Chunk Graphs for Token-Budgeted Context Selection in Multi-Hop Retrieval-Augmented Generation
AI 导读
SpectRAG 提出一种图谱增强检索框架，通过混合候选种子、加权块图谱构建、图谱扩展与谱相关性传播，在固定 token 预算下组装上下文。该框架在 MultiHopRAG、UltraDomain 和长文档问答实验中提升了广谱证据召回率，生成质量与 dense、hybrid、HyDE、LightRAG、NaiveRAG 基线相比具有竞争力。
正文 · 原文
Abstract:Retrieval-augmented generation (RAG) systems ground large language models (LLMs) by retrieving external evidence and conditioning generation on the retrieved context. Although dense retrieval is effective for local semantic matching, independently ranked retrieval can return redundant passages, miss cross-chunk dependencies, and provide incomplete evidence for multi-hop reasoning. We propose SpectRAG, a spectral graph-augmented retrieval framework that combines hybrid candidate seeding, weighted chunk graph construction, graph-based expansion, spectral relevance propagation, and token-budgeted context selection. Document chunks are represented by dense semantic embeddings and graph-spectral coordinates derived from a weighted chunk graph whose edges encode semantic similarity, document adjacency, section hierarchy, shared entities, citation links, and similarity between LLM-generated utility questions. At query time, SpectRAG builds a high-recall seed set using exact inner-product search and hybrid relevance signals, expands it over the chunk graph, re-scores candidates using graph proximity and spectral information, and assembles the final context under a fixed token budget. The goal is not merely to retrieve individually similar chunks, but to construct a context that is relevant, diverse, structurally connected, and sufficient for grounded reasoning. Experiments on MultiHopRAG, UltraDomain, and long-document question-answering settings show that SpectRAG improves broad evidence recovery and achieves competitive generation quality against dense, hybrid, HyDE, LightRAG, and NaiveRAG baselines. The results further indicate that graph-spectral structure is particularly useful for inference-oriented and cross-document retrieval, while highlighting trade-offs in early precision, computational cost, and domain-dependent performance.
| Comments: | 26 pages, 5 figures, 10 tables. This work is intended for submission to an IEEE journal |
| Subjects: | Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Information Retrieval (cs.IR) |
| ACM classes: | H.3.3; I.2.7 |
| Cite as: | arXiv:2610.36991 [cs.AI] |
| (or arXiv:2610.36991v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.36991 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Buse Yaren Kazangirler M.Sc. [view email]
[v1]
Tue, 27 Oct 2026 10:38:29 UTC (2,873 KB)
来源：arXiv cs.AI · arxiv.org