桥接辅助约束以解决大型推理模型中的指令遵循问题
Bridging Auxiliary Constraints to Resolve Instruction Following in Large Reasoning Models
AI总结：
针对大型推理模型难以可靠遵循多重约束的问题，提出约束关系图补全框架，通过显式建模约束关系并发现桥接约束，将约束违反率降低39%。
摘要：
大型推理模型（LRMs）在许多任务中展现出令人印象深刻的能力，但在可靠地遵循多个指令方面存在困难，要么无法满足单个约束，要么难以同时平衡相互竞争的约束。我们将这一挑战形式化为约束遵循问题（CAP）。本文引入了一个新颖的框架，通过将指令表示为约束的结构化知识图来解决CAP。我们的方法，约束关系图补全（CRGC），显式建模约束之间的关系，识别遵循挑战，并发现“桥接约束”，帮助模型更好地聚焦和协调需求。桥接约束作为辅助指令，使主要约束更加突出和兼容。与通过通用训练方法增强指令遵循的现有方法不同，CRGC通过利用模型自身的知识来创建更好的生成路径，从而专门提高约束满足度。在三个流行的指令遵循数据集上的实验表明，与标准提示相比，我们的方法将约束违反减少了39%，同时保持了大型推理模型的推理能力。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
