Grammar-constrained decoding enables a new jailbreak (CodeSpear) on LLMs for malicious code, countered by CodeShield which trains models to output harmless honeypot code under GCD while preserving refusals.
Lookahead-then-verify: Reliable constrained decoding for diffusion llms under context-free grammars
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
MEMCoder boosts LLM code generation for private libraries by 16.31% pass@1 via a multi-dimensional evolving memory that distills usage guidelines from execution feedback and combines them with static docs.
citing papers explorer
-
Grammar-Constrained Decoding Can Jailbreak LLMs into Generating Malicious Code
Grammar-constrained decoding enables a new jailbreak (CodeSpear) on LLMs for malicious code, countered by CodeShield which trains models to output harmless honeypot code under GCD while preserving refusals.
-
MEMCoder: Multi-dimensional Evolving Memory for Private-Library-Oriented Code Generation
MEMCoder boosts LLM code generation for private libraries by 16.31% pass@1 via a multi-dimensional evolving memory that distills usage guidelines from execution feedback and combines them with static docs.