arXiv cs.CL· Seunghui Jwa, Minsu Oh, Sangwoo Hong, Yeo Chan Yoon·· 11 小时前AI 评分38
关系知识筛选紧凑知识图谱上下文：Less but Sufficient 方法及外部校验的边界
Less but Sufficient: Relation Knowledge Selects Compact Knowledge-Graph Contexts, and What External Checks Can and Cannot Catch
AI 导读
研究提出用关系知识（手工编写或从带关系路径标注的训练问题中学习）筛选出能推出答案的紧凑知识图谱事实上下文，并配合可推导性检查、一致性检查与验证选择的路由门控。
正文 · 原文
Abstract:Large language models (LLMs) read knowledge-graph facts ranked by relevance, leaving open whether they suffice or conflict. Our checks use relation knowledge, written by hand or learned from training questions labelled with their relation paths. It selects a compact context of facts yielding an answer, and derives it; a derivability check tests whether an answer follows, a consistency check whether facts conflict, and a validation-chosen routing gate decides where the derived answer replaces the LLM's. Seven open LLMs read the compact context better in exact match than relevance-ranked facts; on ComplexWebQuestions (CWQ) they match SubgraphRAG's facts at a quarter of the prompt tokens, and stronger LLMs read SubgraphRAG's better. Where the routing gate passes, ours leads SubgraphRAG's in exact match in all 53 LLM, benchmark and prompt settings. A precision gate, returning the derived answer only when the check passes with exactly one derived entity, answered 18 and 5 percent of held-out WebQSP and CWQ questions in a pre-specified test, right for 90 and 96 percent. The consistency check judges facts by path evidence only where another path joins their entities, true of 2.5 percent of named-entity facts in our compact WebQSP and CWQ contexts.
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2611.01733 [cs.CL] |
| (or arXiv:2611.01733v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2611.01733 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yeochan Yoon [view email]
[v1]
Sun, 1 Nov 2026 09:31:11 UTC (103 KB)
来源：arXiv cs.CL · arxiv.org