arXiv cs.CL· Jing Liu, Yongxing Qi, Muchen Jiang, Chengnan Hu, Qingqing Peng, Haoming Wang, Yuqing Wang, Yang Yu, Xu Zhang, Ting Wu·· 11 小时前AI 评分31
从关联到因果：用因果图与注意力机制提升 RAG 检索精度
From Association to Causation: Improving Retrieval Precision of Retrieval-Augmented Generation via Causal Relations and an Attention Mechanism
AI 导读
研究提出用因果图重构 RAG 的终端检索阶段，将查询与文档共享的关键词视为潜在共同原因 A、文档剩余关键词视为潜在集合 B，以区分关联性与因果性，减少关键词重合但不含所需信息的文档被召回。该方法在检索精度上达到 95% 可靠性，并配有完全本地化的测试环境验证可部署性。
正文 · 原文
Abstract:Retrieval-Augmented Generation (RAG) grounds LLM generation on retrieved documents, but the standard terminal retrieval stage--dense-vector similarity, optionally followed by reranking--often returns documents that share keywords with the query without containing the needed information, a failure mode that grows with the knowledge base. We trace it to a conceptual gap: similarity captures only associational relations, whereas the documents that matter are linked to the query causally. We model the terminal retrieval stage with a causal graph grounded in Reichenbach's common cause principle: the keywords shared by the query and a retrieved document form a latent common cause A, and the document's residual keywords form a latent set B linking the document to the ideal output. Since a retrieved document is a collider (A -> d <- B), retrieval itself opens an associational path between the query and B, which licenses a training-free, attention-style re-scoring rule: the cosine similarity between the query embedding and the weighted centroid embedding of B. Unlike causality-enhanced RAG variants that model causal relations inside the knowledge content, our graph models the causal structure of the retrieval process itself. On a real 471-document enterprise knowledge base, the method promotes a relevant guideline from rank 6 to the top 3; on a controlled diagnostic corpus reproducing the keyword-stuffing regime, it improves the mean target rank from 2.88 to 1.25, while a trained cross-encoder reranker barely helps (2.63). Conversely, on three BEIR benchmarks the score underperforms the similarity baseline, delineating the applicability boundary: the method guards the keyword-stuffing regime of growing proprietary knowledge bases and complements neural rerankers; a corpus-level calibration gate selects the correct regime with >= 95% reliability. A fully local testbed demonstrates deployability.
| Comments: | 16 pages, 2 figures, 4 tables, 1 algorithm. Code available at this https URL |
| Subjects: | Artificial Intelligence (cs.AI); Computation and Language (cs.CL) |
| ACM classes: | H.3.3; I.2.7 |
| Cite as: | arXiv:2608.21702 [cs.AI] |
| (or arXiv:2608.21702v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2608.21702 arXiv-issued DOI via DataCite |
Submission history
From: Jing Liu [view email]
[v1]
Sat, 22 Aug 2026 00:31:06 UTC (22 KB)
[v2]
Fri, 30 Oct 2026 02:58:02 UTC (22 KB)
来源：arXiv cs.CL · arxiv.org