conftrace_

decoding level

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

harmful output (1) large language model (1) safety mechanism (1) harmful output detection (1) decoding optimization (1) llm safety (1) jailbreak defense (1) speculative decoding (1)

Papers

Root Defense Strategies: Ensuring Safety of LLM at the Decoding Level ACL 2025