REVIEW 6 cited by
Improving LLM Reasoning for Vulnerability Detection via Group Relative Policy Optimization
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Improving LLM Reasoning for Vulnerability Detection via Group Relative Policy Optimization
read the original abstract
Improving and understanding the training dynamics and reasoning of Large Language Models (LLMs) has become essential for their deployment in AI-based security tools, such as software vulnerability detection. In this work, we present an extensive study aimed at advancing recent RL-based finetuning techniques for LLMs in the context of vulnerability detection. We start by highlighting key limitations of commonly adopted LLMs, such as their tendency to over-predict certain types of vulnerabilities while failing to detect others. To address this challenge, we explore the use of Group Relative Policy Optimization (GRPO), a recent policy-gradient method, for guiding LLM behavior through structured, rule-based rewards. We enable its application to the vulnerability detection task by redefining its advantage functions and reward signals using annotations from widely used datasets in the field, including BigVul, DiverseVul, and CleanVul. The proposed methodology enables an extensive set of experiments, addressing multiple research questions regarding the impact of GRPO on generalization, reasoning capabilities, and performance improvements over standard supervised finetuning (SFT). Our findings offer valuable insights into the potential of RL-based training to enhance both the performance and reasoning abilities of LLMs in the context of software vulnerability detection.
Forward citations
Cited by 6 Pith papers
-
Geometric quantification for nonlinear deformation in knitted fabrics
A geometric quantification framework reconstructs yarn centerlines and fabric surfaces from sparse data to quantify how nonlinear deformation distributes among stitch reorientation, loop bending, surface bending, and ...
-
SAGE: Signal-Amplified Guided Embeddings for LLM-based Vulnerability Detection
SAGE uses sparse autoencoders to boost vulnerability signals in LLMs, raising internal SNR 12.7x and delivering up to 318% MCC gains on vulnerability detection benchmarks.
-
CVE-Factory: Scaling Expert-Level Agentic Tasks for Code Security Vulnerability
CVE-Factory automates expert-level creation of executable code vulnerability tasks from sparse CVE data, achieving 95% solution correctness and 96% environment fidelity to build LiveCVEBench and over 1,000 training en...
-
CVE-Factory: Scaling Expert-Level Agentic Tasks for Code Security Vulnerability
CVE-Factory automatically converts CVE metadata into executable vulnerability tasks, yielding a 190-task LiveCVEBench and 1,000+ training tasks that lift fine-tuned Qwen3-32B from 5.3% to 35.8% on that benchmark.
-
VULPO: Context-Aware Vulnerability Detection via On-Policy LLM Optimization
A 4B LLM trained with judge-scored, difficulty-scaled on-policy RL reaches F1 70.45 on context-aware C/C++ vulnerability detection, comparable to DeepSeek-V3.1, with the caveat that the same judge provided the trainin...
-
Geometric quantification for nonlinear deformation in knitted fabrics
A geometric quantification framework reconstructs yarn centerlines and fabric surfaces from sparse knit data and partitions large deformation into stitch reorientation, loop bending, surface bending, and dilation.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.