arXiv cs.AI
· Papers
SyRuP: Enhancing System-Prompt Following via Reward-Guided Prediction in LLM Decoding
arXiv:2607.23991v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly controlled through system prompts that specify roles, styles, formats, and safety requirements. However, models follow these prompts only implicitly through in-context learning, which can be insufficient for complex or compo