arXiv cs.CL· Yifan Yuan, Yancheng Zhu, Zuoyu Zhang, Xiaogang Peng·· 13 小时前AI 评分38
SurveyGraph：用方法-实体知识图谱生成学术综述
SurveyGraph: Generating Academic Surveys via Methods-Entity Knowledge Graphs
AI 导读
SurveyGraph 是一个围绕方法-实体知识图谱（MEKG）构建的学术综述生成框架，MEKG 编码方法层面的后续、竞争与共享资源关系，支撑核心论文发现、检索、混合大纲与证据门控的叙述合成。
正文 · 原文
Abstract:Most automated survey generation systems retrieve papers as flat documents, limiting their ability to capture research structure. We present SurveyGraph, a framework built around a Methods-Entity Knowledge Graph (MEKG) encoding method-level follow-on, competition, and shared-resource relations. The graph supports core-paper discovery, retrieval, hybrid outlining, and evidence-gated narrative synthesis. We evaluate retrieval, semantic edges, citation grounding, collection coverage, and generation-stage components. In a controlled seven-method equal-budget benchmark, MEKG-anchored fusion balances recall and structural density, with an independent co-citation check. In a separate archived graph-native diagnostic, graph-aware retrieval nearly doubles recall over flat lexical baselines across eight runs (p = 0.004). A semantic evidence gate achieves AUC = 0.75. Audits of 160 generated sentences find 80.6% anchored-or-partial citation support. Human adjudication of 108 stratified semantic edges finds 68.5% supported-or-partial relations (binary-support Cohen's kappa = 0.64), with improves strongest (80.6%) and extends weakest (52.8%). A SurveyBench-facing collection probe reaches mean reference coverage of 0.521 across four topics with an eight-paper budget. Same-backend Qwen diagnostics on a 30-paper/74-relation graph show reduced organization signals when hybrid outlining is removed. Concurrent-system comparisons provide bounded context rather than matched-backend end-to-end evidence. The results position MEKG as an auditable structural layer for typed diagnostics, relation-specific filtering, and controlled survey generation. Code and artifacts: this https URL.
| Comments: | Accepted at EMNLP 2026 Findings. 34 pages including appendices |
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Information Retrieval (cs.IR) |
| Cite as: | arXiv:2610.31317 [cs.CL] |
| (or arXiv:2610.31317v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.31317 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yancheng Zhu [view email]
[v1]
Thu, 22 Oct 2026 14:08:59 UTC (6,953 KB)
来源：arXiv cs.CL · arxiv.org