conftrace_

harmful output detection

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

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

Papers

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