Post-Training Large Language Models with LLMON
Large Language Models (LLMs) treat all context tokens uniformly, lacking explicit separation between executable instructions and passive data. This leads to prompt injection vulnerabilities, ambiguous instruction binding, and unreliable execution control. We present a post-training methodology using LLMON (LLM Object N...
Basel Shbita, Michael Hind, Chad DeLuca et al.
· 0 citations