一句话：基于1000个漏洞的实证研究，揭示自然语言与代码中细粒度漏洞实体（触发、现象、修复）的关系模式，并评估自动提取方法。
理解软件漏洞需要分析自然语言描述与源代码中的细粒度实体及其复杂关系。漏洞描述常将触发条件、崩溃现象和修复动作交织在同一句子中，难以区分根因、症状与修复策略；关键实体的缺失进一步阻碍了可追溯性。本文构建了包含1000个漏洞的手工标注数据集，提取短语级的漏洞触发、崩溃现象和修复后实体，将其归入结构化分类体系，并分析自然语言与源代码内部的跨实体关系，揭示了漏洞演化与修复策略中的重复模式。此外，作者研究了自动化实体提取方法，实验表明ELECTRA等预训练语言模型以及基于LLM的方法优于其他方法。
Understanding software vulnerabilities requires analyzing fine-grained entities and their complex relationships across natural language (NL) artifacts and source code. Vulnerability descriptions often interweave vulnerability triggers (VT), crash phenomena (CP), and after-fix (AF) actions within the same sentence, making it challenging to distinguish root causes, failure symptoms, and remediation strategies. Additionally, missing key NL entities further hinders traceability, limiting an analyst’s ability to determine why and how a vulnerability was introduced and resolved. To address these challenges, we conduct an empirical study on fine-grained entity relationships using a manually curated dataset of 1,000 vulnerabilities. We extract phrase-level VT, CP, and AF entities, categorize them into structured taxonomies, and analyze cross-entity relationships within NL artifacts and source code, uncovering recurring patterns in vulnerability evolution and remediation strategies. Furthermore, we investigate the automation of vulnerability entity extraction using different approaches, showing that ELECTRA [7], a state-of-the-art pre-trained language model, along with other LLM-based approaches, outperforms other methods.
@inproceedings{paperbot11928,
title = {An Empirical Study of Fine-Grained Entity Relationships for Tracing Natural Language and Code Vulnerability Artifacts},
author = {Simin Wang and LiGuo Huang and Shiyi Wei and Amiao Gao and Ruiqi Hu and Vincent Ng},
booktitle = {ICSE},
year = {2026},
doi = {10.1145/3744916.3787831}
}