SOURCE-LINKED INTELLIGENCE

Cross-Relational Preference Learning for Better LLM Instruction Following

arXiv · AI, language, vision and robotics · article · Aug 29, 2026 · UTC

Large Language Models (LLMs) still exhibit limited capability in following complex instructions. While existing approaches often rely on preference learning to enhance this ability, they typically overlook the relationships between the permissible response spaces of different instructions, which restricts a model to align with subtle and diverse constraint variations. To address this, we propose Cross-Relational Preference Learning (CRPL), a novel framework for constructing preference data that explicitly models inter-instruction relationships through two key techniques: Cross-Relationship Per

Read original source ↗ Open in workspace

recordType

paper

region

Global