基于部分知识的约束实体选择：面向大语言模型的知识图谱问答
Constrained Entity Selection under Partial Knowledge for LLM-Based Knowledge Graph QA
查看机构详情
- Brandenburg University of Applied Sciences（勃兰登堡应用技术大学）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
针对现有大语言模型知识图谱问答方法的缺陷，提出CES-PK方法，通过轻量符号约束验证LLM生成的候选答案，在Hetionet上验证，实现精确率提升且保持召回率。
中文摘要 AI 辅助
大语言模型正越来越多地被用于知识图谱问答（KGQA），但可能无法正确将答案关联到底层图谱中。当前基于大语言模型的KGQA方法要么依赖于将语义完全解析为可执行查询（如SPARQL），但由于复杂的模式或现实世界知识图谱的不完整性，在实际应用中较为脆弱；要么依赖于大语言模型对知识图谱的推理和答案生成，这种方法可能更具鲁棒性，但缺乏形式化保证。在本研究中，我们探讨一种互补场景：由基于大语言模型的系统生成候选答案，随后使用从问题中导出的轻量符号约束对其进行验证。我们提出了基于部分知识的约束实体选择（CES-PK），这一问题形式化方法聚焦于排除无效答案并为有效答案提供符号支持，无需构建可执行逻辑形式。为解决知识图谱不完整的问题，我们采用三值约束语义（满足、违反、未知），在开放世界假设下避免错误拒绝。为验证所提方法的效果，我们将该框架实例化于Hetionet生物医学知识图谱上，并评估类型、关系和排除约束的影响。实验结果显示，通过过滤无效候选，精确率得到提升；同时由于保留了约束未被明确违反的候选，召回率得以保持；满足的约束还提供了额外的正面符号证据，用于对剩余候选进行排序。
英文摘要
Large language models are increasingly used for knowledge graph question answering (KGQA), but can fail to correctly ground answers in the underlying graph. Current approaches to LLM-based KGQA either rely on full semantic parsing into executable queries such as SPARQL, which is brittle in practice due to complex schemas or incompleteness of real-world KGs, or on LLM-reasoning and answer generation over KGs, which can be more robust but lacks formal guarantees. In this work, we study a complementary setting in which \emph{candidate} answers are generated by an LLM-based system and subsequently verified using lightweight symbolic constraints derived from the question. We introduce \emph{Constrained Entity Selection under Partial Knowledge (CES-PK)}, a problem formulation that focuses on eliminating invalid answers and providing symbolic support for valid ones without requiring construction of executable logical forms. To account for incomplete KGs, we employ a three-valued constraint semantics (\emph{satisfied, violated, unknown}) that avoids incorrect rejections under open-world assumptions. To demonstrate the effects of our method, we instantiate this framework over the Hetionet biomedical knowledge graph and evaluate the impact of type, relation, and exclusion constraints. Experiments show that precision improves by filtering invalid candidates, while recall is preserved due to retaining candidates whose constraints are not explicitly violated. Satisfied constraints provide additional positive symbolic evidence to rank remaining candidates.
