让大模型在不完整知识图谱下推理更可靠
Grounding LLM Reasoning under Incomplete Graph Evidence
- 用图谱中的实体锚点和路径能量构建推理基础
- 发现无法用硬规则同时排除错误和保留未知正确路径
- 提出软约束机制，适合图谱问答与可信生成场景
知识图谱可引导大语言模型推理，但系统所见的图谱通常是检索得到的、部分关联的、有时间范围限制的不完整证据状态，而非真实世界的完整表述。本文从理论角度研究在不完整图谱证据下对大模型推理轨迹的可验证性。该证据状态会引出实体锚点、类型化关系残差、路径能量和支撑区域，而语言模型则提供候选推理路径的先验分布。我们证明，在开放世界不完整性假设下，仅基于可观测状态的任何硬规则都无法同时拒绝所有无支持的错误路径并保留所有真实但未被观测到的路径。随后，我们将软接地定义为对语言模型先验的KL正则化变形：有限松弛可保持对未被支持但不矛盾路径的支持，而硬条件则对应于无穷惩罚极限。该框架还给出了证据扰动下的稳定性边界，并明确了适用于GraphRAG、KGQA、图谱智能体、约束解码和可信生成的约束范式。所有结论均为证据相关：知识图谱兼容性被视为声明支持，而非事实真相。
原文摘要 · Abstract (English)
Knowledge graphs can guide large language models (LLMs) reasoning, but the graph seen by a system is usually a retrieved, linked, temporally scoped, and incomplete evidence state rather than a complete account of truth. We develop a theoretical perspective on grounding observable LLM trajectories under such incomplete graph evidence.The evidence state induces entity anchors, typed relation residuals, path energies, and support regions, while the language model supplies a prior over candidate trajectories. We show that, under open-world incompleteness, no hard rule based only on the observed state can both reject every false unsupported trajectory and retain every true-but-unobserved one.We then characterize soft grounding as a KL-regularized deformation of the LLM prior: finite slack preserves support for unsupported but non-contradicted trajectories, whereas hard conditioning appears as an infinite-penalty limit.The framework also yields stability bounds under evidence perturbations and clarifies the constraint regimes appropriate for GraphRAG, KGQA, graph agents, constrained decoding, and faithful generation. The claims are evidence-relative: KG compatibility is treated as declared support, not factual truth.
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。