Lune

ACL Findings2025

Boosting Vulnerability Detection of LLMs via Curriculum Preference Optimization with Synthetic Reasoning Data

Xin-Cheng Wen, Yijun Yang, Cuiyun Gao, Yang Xiao, Deheng Ye

摘要

Large language models (LLMs) demonstrate considerable proficiency in numerous codingrelated tasks; however, their capabilities in detecting software vulnerabilities remain limited. This limitation primarily stems from two factors: (1) the absence of reasoning data related to vulnerabilities, which hinders the models' ability to capture underlying vulnerability patterns; and (2) their focus on learning semantic representations rather than the reason behind them, thus failing to recognize semantically similar vulnerability samples. Furthermore, the development of LLMs specialized in vulnerability detection is challenging, particularly in environments characterized by the scarcity of high-quality datasets. In this paper, we propose a novel framework ReVD that excels at mining vulnerability patterns through reasoning data synthesizing and vulnerability-specific preference optimization. Specifically, we construct forward and backward reasoning processes for vulnerability and corresponding fixed code, ensuring the synthesis of high-quality reasoning data. Moreover, we design the triplet supervised fine-tuning followed by curriculum online preference optimization for enabling ReVD to better understand vulnerability patterns. The extensive experiments conducted on PrimeVul and SVEN datasets demonstrate that ReVD sets new state-of-the-art for LLM-based software vulnerability detection, e.g., 12.24%-22.77% improvement in the accuracy. The source code and data are available at https: //github.com/Xin-Cheng-Wen/PO4Vul.

问 Lune

几分钟读透这篇 Paper,不用再花一下午。

Lune 能读完全文,也能读引用它的顶会 Paper,讲清它的结论、证据和局限,每一点都注明出自哪篇 Paper。不用硬啃,也不靠猜。

已有 4 篇顶会 Paper 引用了它。别等审稿人问起,先弄清它们发现了什么。

可以从这些问题问起

Lune 可以查阅

全文 · 引用它的顶会 Paper · 相关的 Paper

获取答案

免费开始,无需绑卡

脉络

  • Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation 引用了 Direct Preference Optimization: Your Language Model is Secretly a Reward Model
  • Vul-R2: A Reasoning LLM for Automated Vulnerability Repair 引用了 Data Quality for Software Vulnerability Datasets
  • Repo2Run: Automated Building Executable Environment for Code Repository at Scale 引用了 Vul-R2: A Reasoning LLM for Automated Vulnerability Repair
  • SEER: Enhancing Chain-of-Thought Code Generation through Self-Exploring Deep Reasoning 引用了 Vul-R2: A Reasoning LLM for Automated Vulnerability Repair
  • Data Quality for Software Vulnerability Datasets 引用了 CodeBERT: A Pre-Trained Model for Programming and Natural Languages
它引用的引用它的从左到右按年份排列,引用越多,位置越高。

引用它的顶会 Paper4

  1. Repo2Run: Automated Building Executable Environment for Code Repository at ScaleRuida Hu, Chao Peng, Xinchen Wang, Junjielong Xu 等NeurIPS 2025 · 49 次引用
  2. Vul-R2: A Reasoning LLM for Automated Vulnerability RepairXin-Cheng Wen, Zirui Lin, Yijun Yang, Cuiyun Gao 等ASE 2025 · 1 次引用
  3. SEER: Enhancing Chain-of-Thought Code Generation through Self-Exploring Deep ReasoningShuzheng Gao, Chaozheng Wang, Cuiyun Gao, Michael R. LyuICSE 2026 · 1 次引用
  4. VulInstruct: Teaching LLMs Root-Cause Reasoning for Vulnerability Detection via Security SpecificationsHao Zhu, Jia Li, Cuiyun Gao, Jiaru Qian 等FSE 2026

它引用的 Paper14

  1. Direct Preference Optimization: Your Language Model is Secretly a Reward ModelRafael Rafailov, Archit Sharma, Eric Mitchell, Christopher D. Manning 等NeurIPS 2023 · 10,924 次引用
  2. CodeBERT: A Pre-Trained Model for Programming and Natural LanguagesZhangyin Feng, Daya Guo, Duyu Tang, Nan Duan 等EMNLP Findings 2020 · 2,828 次引用
  3. Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine TranslationHaoran Xu, Amr Sharaf, Yunmo Chen, Weiting Tan 等ICML 2024 · 447 次引用
  4. Enhancing Static Analysis for Practical Bug Detection: An LLM-Integrated ApproachHaonan Li, Yu Hao, Yizhuo Zhai, Zhiyun QianOOPSLA 2024 · 142 次引用
  5. Data Quality for Software Vulnerability DatasetsRoland Croft, Muhammad Ali Babar, M. Mehdi KholoosiICSE 2023 · 138 次引用

相关 Paper

  1. Three Heads Are Better Than One: A Multi-perspective Reasoning Framework for Enhanced Vulnerability DetectionXin Peng, Bo Lin, Jing Wang, Xiaoling Li 等FSE 2026 · 1 次引用
  2. RealVul: Can We Detect Vulnerabilities in Web Applications with LLM?Di Cao, Yong Liao, Xiuwei ShangEMNLP 2024 · 11 次引用
  3. Vulnerability Detection with Code Language Models: How Far are We?Yangruibo Ding, Yanjun Fu, Omniyyah Ibrahim, Chawin Sitawarin 等ICSE 2025 · 44 次引用
  4. Enhancing Vulnerability Detection via Inter-procedural Semantic CompletionBozhi Wu, Chengjie Liu, Zhiming Li, Yushi Cao 等ISSTA 2025 · 2 次引用
  5. Thought Is All You Need: Smart Contract Vulnerability Detection with Thought-Augmented Large Language ModelChaoyuan Peng, Muhui Jiang, Yajin Zhou, Lei WuFSE 2026
黄昏的海面,两侧是细线勾勒的悬崖