发现文本支持无法保证知识图谱补全的正确性，提出更可靠的证据优先补全策略。
When Correct Edges Cannot Be Verified: A Provenance Gap in Incomplete KGQA and a Provenance-Favoring Completion Policy
- 在推理断点检索证据，通过轻量循环验证候选补全
- 96%正确补全边无文本支持，证明文本来源与正确性脱节
- 适合注重可审计性的场景，牺牲召回换更高证据可信度
不完整知识图谱问答（IKGQA）需补全缺失边以继续推理。现有方法常以文本支持作为补全边质量的代理。我们首次系统检验：文本可验证性是否反映正确性？基于标准随机删除协议提供的真值删除三元组，我们发现：在所有真值正确的补全边中，76-96%在穷尽检索下仍无支持文本，该现象在不同删除率（20%/40%）、数据集（CWQ/WebQSP）和关系类型（结构型、常识型、长尾型）下均稳健存在。多数Freebase风格事实根本不会在文本中以头尾共现形式出现。因此，文本忠实度衡量的是溯源性而非正确性——二者间存在不可弥合的根本差距。进一步发现，95-97%的正确答案不依赖任何无支持的补全边，故核心问题从“边是否正确”转变为“在溯源不确定时应承认或放弃”。据此提出TGComplete策略：在推理断点检索证据，轻量循环验证，无支持则放弃。相比生成补全基线GoG，其边精度更高（15-21% vs 3-14%），EM指标无显著损失，且承认边的严格忠实度提升3.1-7.4倍，代价是召回降低。我们认为TGComplete并非全面更优，而是精度/溯源/召回权衡中的一个原则性选择，适用于需要可审计的场景。
原文摘要 · Abstract (English)
Incomplete Knowledge Graph Question Answering (IKGQA) requires completing missing edges to continue reasoning. A growing line of work verifies completed edges against retrieved text, treating textual support as a proxy for edge quality. We ask a question that, to our knowledge, has not been systematically tested: does textual verifiability actually track correctness? Exploiting the gold deleted triples provided by the standard random-deletion protocol, we measure both. The finding is counterintuitive: among gold-correct completed edges, 76-96% have no supporting passage even under exhaustive retrieval, robustly across deletion rates (20%/40%), datasets (CWQ/WebQSP), and relation types (structural, commonsense, long-tail). Most Freebase-style facts simply do not occur as head-tail co-mentions in text. Textual faithfulness therefore measures provenance, not correctness -- separated by a paradigm-level gap no in-corpus retrieval closes. This reframes edge completion. Since most completed edges -- correct or not -- are causally redundant for the answer (95-97% of correct answers do not depend on any unsupported edge), the central question shifts from "is the edge correct?" to "admit or abstain under provenance uncertainty?" Within this framing we present TGComplete, a provenance-favoring admission policy that retrieves evidence at a reasoning breakpoint, verifies a candidate through a lightweight loop, and abstains when support is absent. Against the generate-to-complete baseline GoG, it attains higher edge precision against gold (15-21% vs 3-14%), with no statistically detectable EM loss and 3.1-7.4 times higher strict faithfulness of admitted edges -- at the cost of lower recall. We position TGComplete not as uniformly better, but as a principled point on a precision/provenance-recall trade-off, appropriate when auditability matters.
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。