conftrace_

token-level refinement

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (2) real-time verification (1) streaming verification (1) token refinement (1) language model optimization (1) response verification (1) on-the-fly correction (1) token generation (1) adaptive decoding (1) jailbreak defense (1)

Papers

Efficient Real-time Refinement of Language Model Text Generation EMNLP 2025 Alignment-Enhanced Decoding: Defending Jailbreaks via Token-Level Adaptive Refining of Probability Distributions EMNLP 2024