PromptAudit evaluates five prompting strategies across five LLMs on 1000 CVEs and finds chain-of-thought prompting yields the strongest overall performance while adaptive chain-of-thought and self-consistency reduce effective results.
Title resolution pending
5 Pith papers cite this work, alongside 1 external citations. Polarity classification is still indexing.
5
Pith papers citing it
1
external citations · external index
representative citing papers
Fine-tuned decoder-only LLMs fall into a Semantic Trap on vulnerability detection, achieving high scores on unpaired normal code but failing on paired vulnerable-patched code, semantic perturbations, and gap analysis, while reasoning supervision reduces symptoms at the cost of recall.
Text fine-tuning of 8B LLMs on C/C++ vulnerability data inflates cross-language false-positive rates through surface-cue memorization, which an AST inference probe can partially reverse while direct AST fine-tuning cannot.
ZoFia is a zero-shot fake news detection framework that uses hierarchical entity salience retrieval followed by multi-LLM adversarial debate to improve robustness over single-model approaches.
Fine-tuning codegen-mono on 500 synthetic-plus-reviewed Python examples produces 99% accuracy, 98.08% precision, 100% recall and 99.04% F1 for CWE detection.
citing papers explorer
-
PromptAudit: Auditing Prompt Sensitivity in LLM-Based Vulnerability Detection
PromptAudit evaluates five prompting strategies across five LLMs on 1000 CVEs and finds chain-of-thought prompting yields the strongest overall performance while adaptive chain-of-thought and self-consistency reduce effective results.
-
Do Fine-Tuned LLMs Understand Vulnerabilities? An Investigation into the Semantic Trap
Fine-tuned decoder-only LLMs fall into a Semantic Trap on vulnerability detection, achieving high scores on unpaired normal code but failing on paired vulnerable-patched code, semantic perturbations, and gap analysis, while reasoning supervision reduces symptoms at the cost of recall.
-
How Code Representation Shapes False-Positive Dynamics in Cross-Language LLM Vulnerability Detection
Text fine-tuning of 8B LLMs on C/C++ vulnerability data inflates cross-language false-positive rates through surface-cue memorization, which an AST inference probe can partially reverse while direct AST fine-tuning cannot.
-
ZoFia: Zero-Shot Fake News Detection with Entity-Guided Retrieval and Multi-LLM Interaction
ZoFia is a zero-shot fake news detection framework that uses hierarchical entity salience retrieval followed by multi-LLM adversarial debate to improve robustness over single-model approaches.
-
Case Study: Fine-tuning Small Language Models for Accurate and Private CWE Detection in Python Code
Fine-tuning codegen-mono on 500 synthetic-plus-reviewed Python examples produces 99% accuracy, 98.08% precision, 100% recall and 99.04% F1 for CWE detection.