Saved in:
Bibliographic Details
Main Authors: Liu, Yinqi, Zhu, Yueqi, Zhang, Yongkang, Liu, Feiran, Shen, Yutong, Sun, Yufei, Wang, Xin, Liang, Renzhao, Wang, Yidong, Wang, Cunxiang
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.09504
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910092443516928
author Liu, Yinqi
Zhu, Yueqi
Zhang, Yongkang
Liu, Feiran
Shen, Yutong
Sun, Yufei
Wang, Xin
Liang, Renzhao
Wang, Yidong
Wang, Cunxiang
author_facet Liu, Yinqi
Zhu, Yueqi
Zhang, Yongkang
Liu, Feiran
Shen, Yutong
Sun, Yufei
Wang, Xin
Liang, Renzhao
Wang, Yidong
Wang, Cunxiang
contents Scientific surveys require not only summarizing large bodies of literature, but also organizing them into clear and coherent conceptual structures. However, existing automatic survey generation methods typically focus on linear text generation and struggle to explicitly model hierarchical relations among research topics and structured methodological comparisons, resulting in substantial gaps in structural organization and evidence presentation compared to expert-written surveys. To address this limitation, we propose MVSS, a multi-view structured survey generation framework that jointly generates and aligns citation-grounded hierarchical trees, structured comparison tables, and survey text. MVSS follows a structure-first paradigm: it first constructs a tree that captures the conceptual organization of a research domain, then generates comparison tables constrained by the tree structure, and finally uses both the tree and tables as joint structural constraints to guide outline construction and survey text generation. This design enables complementary and aligned multi-view representations across structure, comparison, and narrative. In addition, we introduce a dedicated evaluation framework that systematically assesses generated surveys from multiple dimensions, including structural quality, comparative completeness, and citation fidelity. Through large-scale experiments on 76 computer science topics, we demonstrate that MVSS significantly outperforms existing methods in survey organization and evidence grounding, and achieves performance comparable to expert-written surveys across multiple evaluation metrics.
format Preprint
id arxiv_https___arxiv_org_abs_2601_09504
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle MVSS: A Unified Framework for Multi-View Structured Survey Generation
Liu, Yinqi
Zhu, Yueqi
Zhang, Yongkang
Liu, Feiran
Shen, Yutong
Sun, Yufei
Wang, Xin
Liang, Renzhao
Wang, Yidong
Wang, Cunxiang
Computation and Language
Scientific surveys require not only summarizing large bodies of literature, but also organizing them into clear and coherent conceptual structures. However, existing automatic survey generation methods typically focus on linear text generation and struggle to explicitly model hierarchical relations among research topics and structured methodological comparisons, resulting in substantial gaps in structural organization and evidence presentation compared to expert-written surveys. To address this limitation, we propose MVSS, a multi-view structured survey generation framework that jointly generates and aligns citation-grounded hierarchical trees, structured comparison tables, and survey text. MVSS follows a structure-first paradigm: it first constructs a tree that captures the conceptual organization of a research domain, then generates comparison tables constrained by the tree structure, and finally uses both the tree and tables as joint structural constraints to guide outline construction and survey text generation. This design enables complementary and aligned multi-view representations across structure, comparison, and narrative. In addition, we introduce a dedicated evaluation framework that systematically assesses generated surveys from multiple dimensions, including structural quality, comparative completeness, and citation fidelity. Through large-scale experiments on 76 computer science topics, we demonstrate that MVSS significantly outperforms existing methods in survey organization and evidence grounding, and achieves performance comparable to expert-written surveys across multiple evaluation metrics.
title MVSS: A Unified Framework for Multi-View Structured Survey Generation
topic Computation and Language
url https://arxiv.org/abs/2601.09504