Elamur Research⌕
☰
home / papers / 2025 / 华谱通: 基于知识推理的家谱问答大语言模型

华谱通: 基于知识推理的家谱问答大语言模型

Summary

Retrieval-augmented LLMs often fail at family-tree questions. Genealogical data is heterogeneous, autonomous, complex and evolving (the HACE properties). Family records typically store only parent–child and spouse links. Namesakes or several kinship paths between two people also flood retrieval with redundant candidates. The authors present Huaputong, a Chinese genealogy Q&A system that combines an LLM with knowledge-graph reasoning.

Family data from the Huapu platform is converted to RDF and queried with SPARQL. A Jena reasoner with custom rules then derives kin relations that are absent from the records, such as ancestors, uncles, nephews and in-laws, which raises retrieval recall. To keep prompts precise, the LLM first turns the user's question into question-condition triples. These triples are matched against candidates to tell apart people with the same name. A Dijkstra-style search using a max heap ranks the alternative relation paths. The filtered facts are passed to the LLM through multi-turn prompt templates.

The system is publicly deployed on the Huapu website and was checked on real family records. It shows that rule-based KG reasoning can reduce hallucination where similarity-based retrieval breaks down.

Key points

  • The knowledge base holds 1,900+ genealogies and over 18 million person records. They were originally stored in Neo4j and are served as RDF via Jena/Fuseki.
  • The source graphs contain only five base relations (father, son, daughter, husband, wife). Huaputong defines Jena inference rules for 26 relation types, including recursive ones like ancestor and descendant.
  • Information filtering has two parts:
    • multi-condition matching on question-condition triples, for name ambiguity;
    • max-heap Dijkstra path ranking, for multiple kinship paths.
  • The system is deployed at zhonghuapu.com (Huaputong section). Jena deployment code is on GitHub (lazyloafer/Huaputong).
  • The main baseline being improved on is the document- or similarity-based RAG approach. Text2Query-style KG retrieval also struggles because the underlying graphs are incomplete.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

Fields: Linguistics & languages · Natural language processing

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.13328/j.cnki.jos.007399

@article{2025,
  title = {{华谱通: 基于知识推理的家谱问答大语言模型}},
  author = {吴信东 and 卓兴锐 and 常永泮 and 吴共庆 and 张赞 and 朱毅},
  journal = {软件学报 (Journal of Software)},
  year = {2025},
  doi = {10.13328/j.cnki.jos.007399},
  url = {https://doi.org/10.13328/j.cnki.jos.007399}
}

References

46 references, 7 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Wu XD, Li J, Zhou P, Bu CY. Fusion technique for fragmented genealogy data. Ruan Jian Xue Bao/Journal of Software, 2021, 32(9): 2816–2836 (in Chinese with English abstract). http://www.jos.org.cn/1000-9825/6010.htm [doi: 10.13328/j.cnki.jos.006010] — [doi:10.13328/j.cnki.jos.006010](https://doi.org/10.13328/j.cnki.jos.006010) ↗
  2. Wu XD, Jiang TT, Zhu Y, Bu CY. Knowledge graph for China’s genealogy. IEEE Trans. on Knowledge and Data Engineering, 2023, 35(1): 634–646. [doi: 10.1109/TKDE.2021.3073745] — [doi:10.1109/tkde.2021.3073745](https://doi.org/10.1109/tkde.2021.3073745) find
  3. Wu XD, Sheng SJ, Jiang TT, Bu CY, Wu MH. Huapu-CP: From knowledge graphs to a data central-platform. Acta Automatica Sinica, 2020, 46(10): 2045–2059 (in Chinese with English abstract). [doi: 10.16383/j.aas.c200502] — [doi:10.16383/j.aas.c200502](https://doi.org/10.16383/j.aas.c200502) find
  4. Wu XD, Chen HH, Wu GQ, Liu J, Zheng QH, He XF, Zhou AY, Zhao ZQ, Wei BF, Li Y, Zhang QP, Zhang SC. Knowledge engineering with big data. IEEE Intelligent Systems, 2015, 30(5): 46–55. [doi: 10.1109/MIS.2015.56] — [doi:10.1109/mis.2015.56](https://doi.org/10.1109/mis.2015.56) find
  5. Brown TB, Mann B, Ryder N, et al. Language models are few-shot learners. In: Proc. of the 34th Int’l Conf. on Neural Information Processing Systems. Vancouver: Curran Associates Inc., 2020. 1877–1901. find
  6. Yin CL, Du KP, Nong Q, Zhang HC, Yang L, Yan B, Huang X, Wang XB, Zhang X. PowerPulse: Power energy chat model with LLaMA model fine-tuned on Chinese and power sector domain knowledge. Expert Systems, 2024, 41(3): e13513. [doi: 10.1111/exsy.13513] — [doi:10.1111/exsy.13513](https://doi.org/10.1111/exsy.13513) find
  7. Teubner T, Flath CM, Weinhardt C, van der Aalst W, Hinz O. Welcome to the era of ChatGPT et al. Business & Information Systems Engineering, 2023, 65(2): 95–101. [doi: 10.1007/s12599-023-00795-x] — [doi:10.1007/s12599-023-00795-x](https://doi.org/10.1007/s12599-023-00795-x) find
  8. Tay Y, Dehghani M, Bahri D, Metzler D. Efficient transformers: A survey. ACM Computing Surveys, 2023, 55(6): 109. [doi: 10.1145/3530811] — [doi:10.1145/3530811](https://doi.org/10.1145/3530811) find
  9. Ji ZW, Lee N, Frieske R, Yu TZ, Su D, Xu Y, Ishii E, Bang YJ, Madotto A, Fung P. Survey of hallucination in natural language generation. ACM Computing Surveys, 2023, 55(12): 248. [doi: 10.1145/3571730] find our card
  10. Pan SR, Luo LH, Wang YF, Chen C, Wang JP, Wu XD. Unifying large language models and knowledge graphs: A roadmap. IEEE Trans. on Knowledge and Data Engineering, 2024, 36(7): 3580–3599. [doi: 10.1109/TKDE.2024.3352100] find our card
  11. Chen JW, Lin HY, Han XP, Sun L. Benchmarking large language models in retrieval-augmented generation. In: Proc. of the 38th AAAI Conf. on Artificial Intelligence. Vancouver: AAAI Press, 2024. 17754–17762. [doi: 10.1609/aaai.v38i16.29728] find our card
  12. Wu XD, Zhu XQ, Wu GQ, Ding W. Data mining with big data. IEEE Trans. on Knowledge and Data Engineering, 2014, 26(1): 97–107. [doi: 10.1109/TKDE.2013.109] — [doi:10.1109/tkde.2013.109](https://doi.org/10.1109/tkde.2013.109) find
  13. Lewis P, Perez E, Piktus A, Petroni F, Karpukhin V, Goyal N, Küttler H, Lewis M, Yih WT, Rocktäschel T, Riedel S, Kiela D. Retrieval-augmented generation for knowledge-intensive NLP tasks. In: Proc. of the 34th Int’l Conf. on Neural Information Processing Systems. Vancouver: Curran Associates Inc.,… find
  14. Futia G, Vetro A, Melandri A, De Martin JC. Training neural language models with SPARQL queries for semi-automatic semantic mapping. Procedia Computer Science, 2018, 137: 187–198. [doi: 10.1016/j.procs.2018.09.018] — [doi:10.1016/j.procs.2018.09.018](https://doi.org/10.1016/j.procs.2018.09.018) find
  15. Sun JS, Xu CJ, Tang LMY, Wang SZ, Lin C, Gong YY, Ni LM, Shum HY, Guo J. Think-on-graph: Deep and responsible reasoning of large language model on knowledge graph. In: Proc. of the 12th Int’l Conf. on Learning Representations. Vienna: OpenReview.net, 2024. 1–31. find
  16. Ma YB, Cao YX, Hong Y, Sun AX. Large language model is not a good few-shot information extractor, but a good reranker for hard samples. In: Proc. of the 2023 Findings of the Association for Computational Linguistics: EMNLP. Singapore: Association for Computational Linguistics, 2023. 10572–10601. [do… find
  17. Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser Ł, Polosukhin I. Attention is all you need. In: Proc. of the 34th Int’l Conf. on Neural Information Processing Systems. Long Beach: Curran Associates Inc., 2017. 6000–6010. find
  18. Wang NY, Ye YX, Liu L, Feng LZ, Bao T, Peng T. Language models based on deep learning: A review. Ruan Jian Xue Bao/Journal of Software, 2021, 32(4): 1082–1115 (in Chinese with English abstract). http://www.jos.org.cn/1000-9825/6169.htm [doi: 10.13328/j.cnki. jos.006169] — [doi:10.13328/j.cnki](https://doi.org/10.13328/j.cnki) ↗
  19. Li ZY, Zhu HX, Lu ZR, Yin M. Synthetic data generation with large language models for text classification: Potential and limitations. In: Proc. of the 2023 Conf. on Empirical Methods in Natural Language Processing. Singapore: Association for Computational Linguistics, 2023. 10443–10461. [doi: 10.186… find our card
  20. Li G, Peng X, Wang QX, Xie T, Jin Z, Wang J, Ma XX, Li XD. Challenges from LLMs as a natural language based human-machine collaborative tool for software development and evolution. Ruan Jian Xue Bao/Journal of Software, 2023, 34(10): 4601–4606 (in Chinese with English abstract). http://www.jos.org.c… — [doi:10.13328/j.cnki.jos.007008](https://doi.org/10.13328/j.cnki.jos.007008) ↗
  21. Zhao ZH, Fan WQ, Li JT, Liu YQ, Mei XW, Wang YQ, Wen Z, Wang F, Zhao XY, Tang JL, Li Q. Recommender systems in the era of large language models (LLMs). IEEE Trans. on Knowledge and Data Engineering, 2024, 36(11): 6889–6907. [doi: 10.1109/TKDE.2024.3392335] — [doi:10.1109/tkde.2024.3392335](https://doi.org/10.1109/tkde.2024.3392335) find
  22. Devlin J, Chang MW, Lee K, Toutanova K. BERT: Pre-training of deep bidirectional Transformers for language understanding. In: Proc. of the 2019 Conf. of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Minneapolis: Association for Computationa… find
  23. Li SC, Wang ZQ, Zhou GD. LLM enhanced cross domain aspect-based sentiment analysis. Ruan Jian Xue Bao/Journal of Software, 2025, 36(2): 644–659 (in Chinese with English abstract). http://www.jos.org.cn/1000-9825/7156.htm [doi: 10.13328/j.cnki.jos.007156] — [doi:10.13328/j.cnki.jos.007156](https://doi.org/10.13328/j.cnki.jos.007156) ↗
  24. Liang Z, Wang HZ, Dai JJ, Shao XY, Ding XO, Mu TY. Interpretability of entity matching based on pre-trained language model. Ruan Jian Xue Bao/Journal of Software, 2023, 34(3): 1087–1108 (in Chinese with English abstract). http://www.jos.org.cn/1000-9825/6794. htm [doi: 10.13328/j.cnki.jos.006794] — [doi:10.13328/j.cnki.jos.006794](https://doi.org/10.13328/j.cnki.jos.006794) ↗
  25. Ju SG, Huang FY, Sun JP. Idiom cloze algorithm integrating with pre-trained language model. Ruan Jian Xue Bao/Journal of Software, 2022, 33(10): 3793–3805 (in Chinese with English abstract). http://www.jos.org.cn/1000-9825/6307.htm [doi: 10.13328/j.cnki.jos.006307] — [doi:10.13328/j.cnki.jos.006307](https://doi.org/10.13328/j.cnki.jos.006307) ↗
  26. Shi D, You CB, Huang JT, Li TH, Xiong DY. CORECODE: A common sense annotated dialogue dataset with benchmark tasks for Chinese large language models. In: Proc. of the 38th AAAI Conf. on Artificial Intelligence. Vancouver: AAAI Press, 2024. 18952–18960. [doi: 10.1609/aaai.v38i17.29861] — [doi:10.1609/aaai.v38i17.29861](https://doi.org/10.1609/aaai.v38i17.29861) find
  27. Xu P, Patwary M, Shoeybi M, Puri R, Fung P, Anandkumar A, Catanzaro B. MEGATRON-CNTRL: Controllable story generation with external knowledge using large-scale language models. In: Proc. of the 2020 Conf. on Empirical Methods in Natural Language Processing. Pennsylvania: Association for Computational… find
  28. Verma G, Rossi R, Tensmeyer C, Gu JX, Nenkova A. Learning the visualness of text using large vision-language models. In: Proc. of the 2023 Conf. on Empirical Methods in Natural Language Processing. Singapore: Association for Computational Linguistics, 2023. 2394–2408. [doi: 10.18653/v1/2023.emnlp-ma… find
  29. Wu TY, He SZ, Liu JP, Sun SQ, Liu K, Han QL, Tang Y. A brief overview of ChatGPT: The history, status quo and potential future development. IEEE/CAA Journal of Automatica Sinica, 2023, 10(5): 1122–1136. [doi: 10.1109/JAS.2023.123618] — [doi:10.1109/jas.2023.123618](https://doi.org/10.1109/jas.2023.123618) find
  30. Ouyang L, Wu J, Jiang X, Almeida D, Wainwright CL, Mishkin P, Zhang C, Agarwal S, Slama K, Ray A, Schulman J, Hilton J, Kelton F, Miller L, Simens M, Askell A, Welinder P, Christiano P, Leike J, Lowe R. Training language models to follow instructions with human feedback. In: Proc. of the 2022 Annual… find
  31. Chowdhery A, Narang S, Devlin J, et al. PaLM: Scaling language modeling with pathways. Journal of Machine Learning Research, 2023, 24(240): 1–113. find
  32. Raffel C, Shazeer N, Roberts A, Lee K, Narang S, Matena M, Zhou YQ, Li W, Liu PJ. Exploring the limits of transfer learning with a unified text-to-text transformer. The Journal of Machine Learning Research, 2020, 21(140): 1–67. find
  33. Li S, Chen JJ, Yuan SY, Wu XY, Yang H, Tao SM, Xiao YH. Translate meanings, not just words: IdiomKB’s role in optimizing idiomatic translation with language models. In: Proc. of the 38th AAAI Conf. on Artificial Intelligence. Vancouver: AAAI Press, 2024. 18554–18563. [doi: 10.1609/aaai.v38i17.29817] — [doi:10.1609/aaai.v38i17.29817](https://doi.org/10.1609/aaai.v38i17.29817) find
  34. Du ZX, Qian YJ, Liu X, Ding M, Qiu JZ, Yang ZL, Tang J. GLM: General language model pretraining with autoregressive blank infilling. In: Proc. of the 60th Annual Meeting of the Association for Computational Linguistics. Dublin: Association for Computational Linguistics, 2022. 320–335. [doi: 10.18653… find our card
  35. Wang L, Ma YY, Bi WS, Lv HL, Li YX. An entity extraction pipeline for medical text records using large language models: Analytical study. Journal of Medical Internet Research, 2024, 26: e54580. [doi: 10.2196/54580] — [doi:10.2196/54580](https://doi.org/10.2196/54580) find
  36. Bi KF, Xie LX, Zhang HH, Chen X, Gu XT, Tian Q. Accurate medium-range global weather forecasting with 3D neural networks. Nature, 2023, 619(7970): 533–538. [doi: 10.1038/s41586-023-06185-3] — [doi:10.1038/s41586-023-06185-3](https://doi.org/10.1038/s41586-023-06185-3) find
  37. Li XL, Liang P. Prefix-tuning: Optimizing continuous prompts for generation. In: Proc. of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th Int’l Joint Conf. on Natural Language Processing (Vol. 1: Long Papers). Pennsylvania: Association for Computational Linguist… find
  38. Zhang ZY, Han X, Liu ZY, Jiang X, Sun MS, Liu Q. ERNIE: Enhanced language representation with informative entities. In: Proc. of the 57th Conf. of the Association for Computational Linguistics. Florence: Association for Computational Linguistics, 2019. 1441–1451. [doi: 10.18653/v1/P19-1139] find
  39. Robertson S, Zaragoza H. The probabilistic relevance framework: BM25 and beyond. Foundations and Trends ® in Information Retrieval, 2009, 3(4): 333–389. [doi: 10.1561/1500000019] find
  40. Agrawal S, Zhou CT, Lewis M, Zettlemoyer L, Ghazvininejad M. In-context examples selection for machine translation. In: Proc. of the 2023 Findings of the Association for Computational Linguistics. Toronto: Association for Computational Linguistics, 2023. 8857–8873. [doi: 10.18653/v1/2023.findings-ac… find our card
  41. Qiao SJ, Yang GP, Yu Y, Han N, Tan X, Qu LL, Ran LQ, Li H. QA-KGNet: Language model-driven knowledge graph question-answering model. Ruan Jian Xue Bao/Journal of Software, 2023, 34(10): 4584–4600 (in Chinese with English abstract). http://www.jos.org.cn/1000-9825/6882.htm [doi: 10.13328/j.cnki.jos.… ↗ our card
  42. Luo LH, Li YF, Haffari G, Pan SR. Reasoning on graphs: Faithful and interpretable large language model reasoning. In: Proc. of the 12th Int’l Conf. on Learning Representations. Vienna: OpenReview.net, 2024. 1–24. find
  43. Avila CVS, Vidal VMP, Franco W, Casanova MA. Experiments with text-to-SPARQL based on ChatGPT. In: Proc. of the 18th IEEE Int’l Conf. on Semantic Computing. Laguna Hills: IEEE, 2024. 277–284. [doi: 10.1109/ICSC59802.2024.00050] — [doi:10.1109/icsc59802.2024.00050](https://doi.org/10.1109/icsc59802.2024.00050) find
  44. Shao JX, Liu GL, Ji SW. An abnormal data analysis and processing method for genealogy graph databases. In: Proc. of the 2020 IEEE Int’l Conf. on Knowledge Graph. Nanjing: IEEE, 2020. 131–136. [doi: 10.1109/ICBK50248.2020.00028] — [doi:10.1109/icbk50248.2020.00028](https://doi.org/10.1109/icbk50248.2020.00028) find
  45. Peng YW, Jiang H, Li RR, Peng ZY. PZXG: A genealogy data service platform for kinship management and application. In: Proc. of the 2020 IEEE Int’l Conf. on Knowledge Graph. Nanjing: IEEE, 2020. 505–512. [doi: 10.1109/ICBK50248.2020.00077] — [doi:10.1109/icbk50248.2020.00077](https://doi.org/10.1109/icbk50248.2020.00077) find
  46. Dong BB, Zhang Z, Li J, Zhu Y, Bu CY, Wu XD. Hypernode: Entity fusion for data traceability and link prediction. In: Proc. of the 2022 IEEE Int’l Conf. on Data Mining. Orlando: IEEE, 2022. 111–120. [doi: 10.1109/ICDM54844.2022.00021] 附中文参考文献: [1] 吴信东, 李娇, 周鹏, 卜晨阳. 碎片化家谱数据的融合技术. 软件学报, 2021, 32(9): 28… — [doi:10.1109/icdm54844.2022.00021](https://doi.org/10.1109/icdm54844.2022.00021) find

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/wu-2025-huaputong-large-language/