arXiv：cs.AI· Cosimo Gregucci, Bo Xiong, Daniel Hernandez, Lorenzo Loconte, Pasquale Minervini, Steffen Staab, Antonio Vergari·· 5 小时前
复杂查询问答真的复杂吗？现有 CQA 基准被指失真
Is Complex Query Answering Really Complex?
AI 导读
研究发现，知识图谱复杂查询问答（CQA）现有基准并不如想象中复杂，部分查询类型中高达 98% 的查询可归约为链接预测等更简单问题。在无法归约的查询上，当前 SOTA CQA 模型性能大幅下降。作者据此提出一组需多跳推理的新基准，系统性实验显示现有方法仍有明显不足。
正文
Abstract:Complex query answering (CQA) on knowledge graphs (KGs) is gaining momentum as a challenging reasoning task. In this paper, we show that the current benchmarks for CQA might not be as complex as we think, as the way they are built distorts our perception of progress in this field. For example, we find that in these benchmarks, most queries (up to 98% for some query types) can be reduced to simpler problems, e.g., link prediction, where only one link needs to be predicted. The performance of state-of-the-art CQA models decreases significantly when such models are evaluated on queries that cannot be reduced to easier types. Thus, we propose a set of more challenging benchmarks composed of queries that require models to reason over multiple hops and better reflect the construction of real-world KGs. In a systematic empirical investigation, the new benchmarks show that current methods leave much to be desired from current CQA methods.
| Comments: | ICML 2025 |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2410.12537 [cs.LG] |
| (or arXiv:2410.12537v4 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2410.12537 arXiv-issued DOI via DataCite |
Submission history
From: Cosimo Gregucci [view email]
[v1]
Wed, 16 Oct 2024 13:19:03 UTC (384 KB)
[v2]
Tue, 18 Feb 2025 12:40:13 UTC (483 KB)
[v3]
Thu, 3 Jul 2025 08:36:22 UTC (486 KB)
[v4]
Mon, 12 Oct 2026 16:21:44 UTC (481 KB)
来源：arXiv：cs.AI · arxiv.org