MUSE Lab
All featured work全部代表作

EMNLP 2026

SurveyGraph

SurveyGraph: Generating Academic Surveys via Methods-Entity Knowledge Graphs

An AI that first maps how a research field evolved, then writes a fully cited survey along that map.

让 AI 先画出一个领域的“方法—实体”知识图谱,再沿着它写出一篇有据可查的学术综述。

Yifan Yuan, Yancheng Zhu, Zuoyu Zhang, Xiaogang Peng†

Overview概览

Publications are growing so fast that writing a good survey is ever more costly, and current LLM survey generators mostly retrieve papers as a flat pile of independent documents. A good survey explains how a field evolved — which work extends which, which methods compete, which benchmarks mark turning points — structure that similarity-based retrieval cannot see, so generated surveys read like a collage of summaries. SurveyGraph builds a Methods-Entity Knowledge Graph that records follow-on, competition and shared-resource relations between methods, and uses it as the backbone for core-paper discovery, graph-aware retrieval, outline generation and evolution-aware writing. Graph-aware retrieval nearly doubles recall over flat lexical baselines (p = 0.004), and citation audits find that 80.6% of generated sentences are fully or partly supported by the papers they cite.

论文越来越多,写一篇好的综述越来越费时费力,而现有的大模型自动综述系统大多把文献当作一堆彼此独立的文档来检索。好的综述要讲清楚一个领域如何演化——哪项工作延续了谁、哪些方法相互竞争、哪些基准标志着转折,只按相似度检索看不到这些结构,生成的综述容易变成零散摘要的拼贴。SurveyGraph 构建“方法—实体知识图谱”(MEKG),显式记录方法之间的延续、竞争和共享资源等关系,并以它为主干完成核心论文发现、图感知检索、大纲生成和按演化脉络组织的写作。图感知检索的召回率接近平面检索基线的两倍(p=0.004),引用核查显示 80.6% 的生成句子能在所引文献中找到完全或部分支撑。

Highlights要点

  1. A Methods-Entity Knowledge Graph records which methods extend, compete with or share resources with others, and becomes the survey's backbone.用“方法—实体知识图谱”记录方法之间的延续、竞争和共享资源,作为综述的骨架。
  2. Graph-aware retrieval nearly doubles recall over flat lexical baselines (p = 0.004).图感知检索的召回率接近平面检索基线的两倍(p = 0.004)。
  3. Citation audits find 80.6% of generated sentences fully or partly supported by the papers they cite.引用核查:80.6% 的生成句子能在所引文献中找到完全或部分支撑。

Method方法

The SurveyGraph pipeline
The SurveyGraph pipeline

Citation引用

@inproceedings{yuan2026surveygraph,
  title     = {SurveyGraph: Generating Academic Surveys via Methods-Entity Knowledge Graphs},
  author    = {Yifan Yuan and Yancheng Zhu and Zuoyu Zhang and Xiaogang Peng},
  booktitle = {Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing},
  year      = {2026},
  url       = {https://arxiv.org/abs/2610.31317}
}

More featured work更多代表作