Lune

ACL Findings2021

Constructing Flow Graphs from Procedural Cybersecurity Texts

Kuntal Kumar Pal, Kazuaki Kashihara, Pratyay Banerjee, Swaroop Mishra, Ruoyu Wang, Chitta Baral

Abstract

Following procedural texts written in natural languages is challenging. We must read the whole text to identify the relevant information or identify the instruction-flow to complete a task, which is prone to failures. If such texts are structured, we can readily visualize instruction-flows, reason or infer a particular step, or even build automated systems to help novice agents achieve a goal. However, this structure recovery task is a challenge because of such texts' diverse nature. This paper proposes to identify relevant information from such texts and generate information flows between sentences. We built a large annotated procedural text dataset (CTFW) in the cybersecurity domain (3154 documents). This dataset contains valuable instructions regarding software vulnerability analysis experiences. We performed extensive experiments on CTFW with our LM-GNN model variants in multiple settings. To show the generalizability of both this task and our method, we also experimented with procedural texts from two other domains (Maintenance Manual and Cooking), which are substantially different from cybersecurity. Our experiments show that Graph Convolution Network with BERT sentence embeddings outperforms BERT in all three domains.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

3 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Business as Rulesual: A Benchmark and Framework for Business Rule Flow Modeling with LLMs cites PAGED: A Benchmark for Procedural Graphs Extraction from Documents
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers3

  1. PAGED: A Benchmark for Procedural Graphs Extraction from DocumentsWeihong Du, Wenrui Liao, Hongru Liang, Wenqiang LeiACL 2024 · 4 citations
  2. Learning Action Conditions from Instructional Manuals for Instruction UnderstandingTe-Lin Wu, Caiqi Zhang, Qingyuan Hu, Alexander Spangher et al.ACL 2023 · 2 citations
  3. Business as Rulesual: A Benchmark and Framework for Business Rule Flow Modeling with LLMsChen Yang, Ruping Xu, Ruizhe Li, Bin Cao et al.ACL 2026 · 1 citation

Builds on3

  1. Commonsense Knowledge Base Completion with Structural and Semantic ContextChaitanya Malaviya, Chandra Bhagavatula, Antoine Bosselut, Yejin ChoiAAAI 2020 · 155 citations
  2. Document Modeling with Graph Attention Networks for Multi-grained Machine Reading ComprehensionBo Zheng, Haoyang Wen, Yaobo Liang, Nan Duan et al.ACL 2020 · 57 citations
  3. Multi-modal Cooking Workflow Construction for Food RecipesLiangming Pan, Jingjing Chen, Jianlong Wu, Shaoteng Liu et al.ACM MM 2020 · 20 citations

Related papers

  1. GraphSkill: Documentation-Guided Agentic Hierarchical Retrieval-Augmented Coding for Complex Graph ReasoningFali Wang, Chenglin Weng, Xianren Zhang, Siyuan Hong et al.KDD 2026
  2. Exploring ChatGPT's Capabilities on Vulnerability ManagementPeiyu Liu, Junming Liu, Lirong Fu, Kangjie Lu et al.USENIX Security 2024 · 52 citations
  3. Co-RedTeam: Orchestrated Security Discovery and Exploitation with LLM AgentsPengfei He, Ash Fox, Lesly Miculicich, Stefan Friedli et al.ICML 2026 · 10 citations
  4. Understanding the Cooking Process with English Recipe TextYi Fan, Anthony HunterACL Findings 2023 · 2 citations
  5. Unsupervised Labeling and Extraction of Phrase-based Concepts in Vulnerability DescriptionsSofonias Yitagesu, Zhenchang Xing, Xiaowang Zhang, Zhiyong Feng et al.ASE 2021 · 18 citations
Dusk over the sea between two cliffs drawn in fine vertical lines