引导解码及其在检索增强生成中的关键作用

摘要

大型语言模型（LLMs）在各类应用中的集成，催生了对结构化且可靠响应的需求。检索增强生成（RAG）系统面临的一个关键挑战是确保输出符合预期格式，同时最大限度地减少幻觉现象。本研究探讨了引导解码在RAG系统中的作用，通过对比三种方法——大纲法、XGrammar法和LM格式强制法——在不同多轮提示设置（零轮、一轮和两轮）下的表现，评估了成功率、幻觉率及输出质量，从而深入理解其性能与适用性。我们的发现揭示了多轮交互如何影响引导解码，揭示了意料之外的性能差异，这些差异可为特定用例的方法选择提供依据。本研究推进了对RAG系统中结构化输出生成的理解，为LLM的部署提供了理论洞见与实践指导。

English

The integration of Large Language Models (LLMs) into various applications has driven the need for structured and reliable responses. A key challenge in Retrieval-Augmented Generation (RAG) systems is ensuring that outputs align with expected formats while minimizing hallucinations. This study examines the role of guided decoding in RAG systems, comparing three methods, Outlines, XGrammar, and LM Format Enforcer, across different multi-turn prompting setups (0-turn, 1-turn, and 2-turn). By evaluating success rates, hallucination rates, and output quality, we provide insights into their performance and applicability. Our findings reveal how multi-turn interactions influence guided decoding, uncovering unexpected performance variations that can inform method selection for specific use cases. This work advances the understanding of structured output generation in RAG systems, offering both theoretical insights and practical guidance for LLM deployment.

引导解码及其在检索增强生成中的关键作用

Guided Decoding and Its Critical Role in Retrieval-Augmented Generation

摘要

Support