DAB biases auto-regressive LLM generation using discrete gradient-based MCMC on an auxiliary token sequence, improving constraint satisfaction with similar fluency and lower per-step cost.
Cold-attack: Jailbreaking llms with stealthiness and controllability
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.CL 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Controlled LLM Decoding via Discrete Auto-regressive Biasing
DAB biases auto-regressive LLM generation using discrete gradient-based MCMC on an auxiliary token sequence, improving constraint satisfaction with similar fluency and lower per-step cost.