零样本构建知识图谱，仅用消费级显卡即可实现高效推理。
Frugal Knowledge Graph Construction with Local LLMs: A Zero-Shot Pipeline, Self-Consistency and Wisdom of Artificial Crowds
- 采用多模型零样本流水线，全程本地推理无需训练。
- 多跳推理准确率达46%，信心路由机制提升至55%。
- 揭示共识悖论：群体一致反可能暗示集体幻觉。
本文提出一种基于本地推理的多模型零样本知识图谱构建与应用流水线，可在消费级硬件上运行。构建了可复现的评估框架，整合DocRED、HotpotQA等外部基准、合成数据及RAGAS评价体系。在500篇文档级别的关系抽取中，零样本F1达0.70±0.041，接近有监督方法DREEAM的0.80。文本转查询任务在200样本上准确率0.80±0.06。多跳推理在500个HotpotQA问题上达到精确匹配（EM）0.46±0.04，RAGAS忠实度为0.96±0.04（50样本）。研究发现：对零温下无法求解的181题，自一致性（k=5, T=0.7）使单个专家模型恢复23%的EM，跨模型最优组合（3架构×5样本）达46.4%。观察到共识悖论：高一致性反而预示集体幻觉。在完整流水线中，自一致性（k=3）将EM从0.46提升至0.48±0.04。信心路由级联机制（Phi-4→GPT-OSS, k=5）实现最优结果0.55±0.04，45.4%问题被重定向。此外，提示工程效果依赖特定模型-提示组合，仅在Gemma-4上有效。整个系统在单张RTX 3090上耗时约5小时，无训练，碳足迹仅0.09 kg CO2 eq。
原文摘要 · Abstract (English)
This paper presents an empirical study of a multi-model zero-shot pipeline for knowledge graph construction and exploitation, executed entirely through local inference on consumer-grade hardware. We propose a reproducible evaluation framework integrating two external benchmarks (DocRED, HotpotQA), WebQuestionsSP-style synthetic data, and the RAGAS evaluation framework in an automated pipeline. On 500 document-level relations, our system achieves an F1 of 0.70 $\pm$ 0.041 in zero-shot, compared to 0.80 for supervised DREEAM. Text-to-query achieves an accuracy of 0.80 $\pm$ 0.06 on 200 samples. Multi-hop reasoning achieves an Exact Match (EM) of 0.46$\pm$0.04 on 500 HotpotQA questions, with a RAGAS faithfulness of 0.96 $\pm$ 0.04 on 50 samples. Beyond the pipeline, we study diversity mechanisms for difficult multi-hop reasoning. On 181 questions unsolvable at zero temperature, self-consistency (k=5, T =0.7) recovers up to 23% EM with a single Mixture-of-Experts (MoE) model, but the cross-model oracle (3 architectures x 5 samples) reaches 46.4%. We highlight an agreement paradox: strong consensus among samples signals collective hallucination rather than a reliable answer, echoing the work of Moussa{ï}d et al. on the wisdom of crowds. Extending to the full pipeline (500 questions), self-consistency (k=3) raises EM from 0.46 to 0.48 $\pm$ 0.04. A confidence-routing cascade mechanism (Phi-4 $\rightarrow$ GPT-OSS, k=5) achieves an EM of 0.55 $\pm$ 0.04, the best result obtained, with 45.4% of questions rerouted. Finally, we show that V3 prompt engineering applied to other models does not reproduce the gains observed with Gemma-4, confirming the specific prompt/model interaction. The entire system runs in $\sim$5 h on a single RTX 3090, without any training, for an estimated carbon footprint of 0.09 kg CO2 eq.
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。