AIBullisharXiv – CS AI · 14h ago6/10
🧠
LsrIF: Enhancing Logic-Structured Instruction Following of Large Language Models
Researchers introduce LsrIF, a training framework that improves how large language models follow complex instructions by recognizing logical structures like sequential dependencies and conditional branching. The method uses structure-aware reward aggregation instead of simple averaging, demonstrating improved instruction-following performance both within and across domains.