An inference-time mixture of linear correction vectors, derived from linear probes on LLM hidden states, improves the security and functionality of code generated by Qwen2.5-Coder and CodeLlama models.
Vul-rag: Enhancing llm-based vulnerability detection via knowledge-level rag
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CR 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
A Mixture of Linear Corrections Generates Secure Code
An inference-time mixture of linear correction vectors, derived from linear probes on LLM hidden states, improves the security and functionality of code generated by Qwen2.5-Coder and CodeLlama models.