Pith. sign in

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 1

years

2025 1

verdicts

CONDITIONAL 1

roles

background 1

polarities

unclear 1

representative citing papers

Controlled LLM Decoding via Discrete Auto-regressive Biasing

cs.CL · 2025-02-06 · conditional · novelty 6.0

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.

citing papers explorer

Showing 1 of 1 citing paper.

  • Controlled LLM Decoding via Discrete Auto-regressive Biasing cs.CL · 2025-02-06 · conditional · none · ref 6

    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.