Luo, L.; Ju, J.; Li, Y.-F.; Haffari, G.; Xiong, B.; Pan, S.: ChatRule: mining logical rules with large language models for knowledge graph reasoning (2023)
0.00
0.0014872681 = product of:
0.0059490725 = sum of:
0.0059490725 = weight(_text_:information in 1171) [ClassicSimilarity], result of:
0.0059490725 = score(doc=1171,freq=2.0), product of:
0.06134496 = queryWeight, product of:
1.7554779 = idf(docFreq=20772, maxDocs=44218)
0.034944877 = queryNorm
0.09697737 = fieldWeight in 1171, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
1.7554779 = idf(docFreq=20772, maxDocs=44218)
0.0390625 = fieldNorm(doc=1171)
0.25 = coord(1/4)
- Abstract
- Logical rules are essential for uncovering the logical connections between relations, which could improve the reasoning performance and provide interpretable results on knowledge graphs (KGs). Although there have been many efforts to mine meaningful logical rules over KGs, existing methods suffer from the computationally intensive searches over the rule space and a lack of scalability for large-scale KGs. Besides, they often ignore the semantics of relations which is crucial for uncovering logical connections. Recently, large language models (LLMs) have shown impressive performance in the field of natural language processing and various applications, owing to their emergent ability and generalizability. In this paper, we propose a novel framework, ChatRule, unleashing the power of large language models for mining logical rules over knowledge graphs. Specifically, the framework is initiated with an LLM-based rule generator, leveraging both the semantic and structural information of KGs to prompt LLMs to generate logical rules. To refine the generated rules, a rule ranking module estimates the rule quality by incorporating facts from existing KGs. Last, a rule validator harnesses the reasoning ability of LLMs to validate the logical correctness of ranked rules through chain-of-thought reasoning. ChatRule is evaluated on four large-scale KGs, w.r.t. different rule quality metrics and downstream tasks, showing the effectiveness and scalability of our method.
