PIPE-Cypher:面向Text-to-Cypher系统的自动企业基准生成
阅读原文· arxiv.orgPIPE-Cypher是一个本地基准生成管道,通过模式分析、反向查询基础、约束生成和确定性Cypher治理,将实时企业属性图和种子查询转化为平衡的自然语言到Cypher基准。使用本地Qwen3.5-9B模型进行生成和评判,导出3000个FinBench/SNB示例,完成三项消融实验,并通过人工标注校准评判行为,评估了11个本地下游模型。生成的基准具有区分性:零样本迁移能力弱,少量样本控制表明模式特定示例库可帮助兼容模型家族。
Enterprise property graphs vary widely in schema structure, internal terminology, domain assumptions, governance constraints, and user interaction patterns. A deployment-relevant Text2Cypher benchmark therefore reflects the questions users and agents actually ask of that graph. Creating such a benchmark is difficult because schemas and values are unique, and graph structure changes over time. Each NL-query pair must also be executable, use real graph entities, preserve diversity, and remain balanced across query types and difficulty levels. We present PIPE-Cypher, a local benchmark-generation pipeline that turns a live property graph and optional seed queries from customer questions, analyst logs, or agent tool calls into balanced NL-to-Cypher benchmarks. PIPE-Cypher combines schema profiling, reverse-query grounding, constrained generation, deterministic Cypher governance, execution validation, redaction, diversity controls, and a calibrated local LLM judge. Using local Qwen3.5-9B generation and judging, PIPE-Cypher exports 3,000 accepted FinBench/SNB examples, completes three audited ablation suites, calibrates judge behavior with human labels, and evaluates 11 local downstream models. The resulting benchmark is deliberately discriminative: zero-shot transfer is weak, while a few-shot control shows that schema-specific example banks can help compatible model families. Together, PIPE-Cypher makes Text2Cypher benchmarking a repeatable process that evolves with the graph, its users, and its target workloads.