通过构建约束关系图，用辅助指令提升大模型对多重指令的遵循能力。
Bridging Auxiliary Constraints to Resolve Instruction Following in Large Reasoning Models
- 将指令建模为约束关系图，显式捕捉约束间关联。
- 引入'桥接约束'使主约束更突出且兼容，减少39%违规。
- 无需额外训练，利用模型自身知识优化生成路径，适合多任务场景。
大型推理模型（LRMs）在诸多任务中表现卓越，但在遵循多个指令时仍存在可靠性问题，或无法满足单个约束，或难以平衡相互冲突的约束。本文将此挑战形式化为约束遵循问题（CAP）。提出一种新框架——约束关系图补全（CRGC），将指令表示为结构化的约束知识图谱，显式建模约束间的关联，识别遵循难点，并发现可帮助模型聚焦与调和要求的“桥接约束”。这些桥接约束作为辅助指令，使主约束更显著且兼容。与依赖通用训练方法提升指令遵循的传统方案不同，CRGC通过利用模型自身知识构建更优生成路径，专门提升约束满足度。在三个主流指令遵循数据集上的实验表明，该方法相比标准提示可降低39%的约束违规，同时保持大型推理模型的推理能力。
原文摘要 · Abstract (English)
Large Reasoning Models (LRMs) have demonstrated impressive capabilities in many tasks, yet they struggle with reliably following multiple instructions, either by failing to satisfy individual constraints or by struggling to balance competing constraints simultaneously. We formalize this challenge as the Constraint Adherence Problem (CAP). This paper introduces a novel framework that addresses CAP by representing instructions as a structured knowledge graph of constraints. Our approach, Constraint Relationship Graph Completion (CRGC), explicitly models relationships between constraints, identifies adherence challenges, and discovers ``bridge constraints'' that help the model better focus on and reconcile requirements. Bridge constraints act as auxiliary instructions that make primary constraints more salient and compatible. Unlike existing approaches that enhance instruction following through general training methods, CRGC specifically improves constraint satisfaction by leveraging the model's own knowledge to create better pathways for generation. Experiments across three popular instruction following datasets demonstrate that our approach reduces constraint violations by 39% compared to standard prompting while maintaining reasoning abilities of large reasoning models.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。