decoding-time-control

Tag

Cards List
#decoding-time-control

SyRuP: Enhancing System-Prompt Following via Reward-Guided Prediction in LLM Decoding

arXiv cs.CL · 2026-07-28 Cached

Introduces SyRuP, a decoding-time framework that trains a cross-attention reward head to produce token-level adherence scores for system prompts, improving LLM following of complex prompts without model tuning.

0 favorites 0 likes
← Back to home

Submit Feedback