Elamur Research⌕
☰
home / papers / 2026 / Subgraph-Guided Executable Logical Form Generation for Knowledge Base Question Answering

Subgraph-Guided Executable Logical Form Generation for Knowledge Base Question Answering

Paper · 2026 · Yuhang Tian, Dandan Song, Zhijing Wu et al.

Summary

LLM-based semantic parsers for Knowledge Base Question Answering (KBQA) usually fetch entities and relations separately, ranked only by semantic similarity. This ignores how the KB is connected and how the question is logically shaped, so crucial relations can be missed and the generated logical forms fail. SELF-KBQA retrieves whole subgraphs instead. First, a fine-tuned Flan-T5-base predicts the question's core reasoning pattern (CRP). A CRP is a topology of up to two hops linking topic and answer entities, including answer-centered variants. Next, candidate subgraphs are enumerated around the linked Freebase entities. They are ranked by combining two signals: structural fit to the predicted CRP and semantic relevance, scored with BGE-M3. The top subgraphs are then condensed under a token budget into a compact context. From this context, an LLM writes S-expressions that are executed against the KB. Experiments on GrailQA, WebQSP and GraphQuestions yield state-of-the-art results. Ablations confirm that both scoring signals and the subgraph context matter. The work shows that structure-aware grounding makes executable, interpretable parsing more reliable.

Key points

  • Two-hop-or-fewer CRP patterns account for 100% of questions in WebQSP, while covering 94.90% in GrailQA and 92.43% in GraphQuestions. CRP prediction accuracy is 85.64% on GrailQA, 87.56% on WebQSP and 76.81% on GraphQuestions.
  • On the GrailQA dev set, the full model reaches EM 82.33 / F1 86.51. Removing the subgraphs drops this to 65.10 / 70.77. Removing the semantic score lowers it to 75.43 / 78.59, and using gold CRPs raises it to 83.77 / 87.89.
  • On GrailQA questions needing three or more hops, the model scores EM 56.4 / F1 62.6, compared with 44.2 / 54.3 for SG-KBQA.
  • End-to-end latency is about 16.9 s per question on one A6000 GPU, and most of that time is BGE-M3 scoring. The authors report this as roughly 25× faster than ChatKBQA and KB-BINDER.
  • When the retrieved subgraphs are supplied in-context to a frozen GPT-4o, F1 rises from 16.1 to 46.9. On the Wikidata-based KQA Pro, CRP coverage is 77.7%.

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

 Institutions

🎓Beijing Institute of TechnologyBeijing · China34 works · 3,652 citations🎓Australian National UniversityCanberra · Australia23 works · 6,522 citations

 Fields, topics and concepts

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 works

🧭 Topics 3Research subjects and languages the work is about.Question answering · 441 worksKnowledge graphs & ontologies · 192 worksSemantic parsing & meaning representation · 185 works

Cite

Cite as Yuhang Tian, Dandan Song, Zhijing Wu, Changzhi Zhou, Jun Yang, Huipeng Ma, Chenhao Li, Luan Zhang, Yading Li, Xudong Li, Shenxi Liu and Jing Jiang. 2026. Subgraph-Guided Executable Logical Form Generation for Knowledge Base Question Answering. Findings of the Association for Computational Linguistics: ACL 2026.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.findings-acl.177

@inproceedings{tian2026subgraph,
  title = {{Subgraph-Guided Executable Logical Form Generation for Knowledge Base Question Answering}},
  author = {Yuhang Tian, Dandan Song, Zhijing Wu, Changzhi Zhou, Jun Yang, Huipeng Ma, Chenhao Li, Luan Zhang, Yading Li, Xudong Li, Shenxi Liu and Jing Jiang},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.177},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.177}
}

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. Sören Auer, Christian Bizer, Georgi Kobilarov, Jens Lehmann, Richard Cyganiak, and Zachary Ives. 2007. Dbpedia: A nucleus for a web of open data. In international semantic web conference, pages 722– 735. Springer. find
  2. Kurt Bollacker, Colin Evans, Praveen Paritosh, Tim Sturge, and Jamie Taylor. 2008. Freebase: a collaboratively created graph database for structuring human knowledge. In Proceedings of the 2008 ACM SIG-MOD international conference on Management of data, pages 1247–1250. find
  3. Liyi Chen, Panrong Tong, Zhongming Jin, Ying Sun, Jieping Ye, and Hui Xiong. 2024. Plan-on-graph: Self-correcting adaptive planning of large language model on knowledge graphs. Advances in Neural Information Processing Systems, 37:37665–37691. find
  4. Tengfei Feng and Liang He. 2025. Rgr-kbqa: Generating logical forms for question answering using knowledge-graph-enhanced large language model. In Proceedings of the 31st International Conference on Computational Linguistics, pages 3057–3070.
  5. Shengxiang Gao, Jey Han Lau, and Jianzhong Qi. 2025. Beyond seen data: Improving KBQA generalization through schema-guided logical form generation. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 8764–8783, Suzhou, China. Association for Computational… find
  6. Yu Gu, Sue Kase, Michelle Vanni, Brian Sadler, Percy Liang, Xifeng Yan, and Yu Su. 2021. Beyond iid: three levels of generalization for question answering on knowledge bases. In Proceedings of the Web Conference 2021, pages 3477–3488. find
  7. Yu Gu and Yu Su. 2022. Arcaneqa: Dynamic program induction and contextualized encoding for knowledge base question answering. In Proceedings of the 29th International Conference on Computational Linguistics, COLING 2022, Gyeongju, Republic of Korea, October 12-17, 2022, pages 1718–1731. Internationa… find
  8. Gaole He, Yunshi Lan, Jing Jiang, Wayne Xin Zhao, and Ji-Rong Wen. 2021. Improving multi-hop knowledge base question answering by learning intermediate supervision signals. In Proceedings of the 14th ACM International Conference on Web Search and Data Mining, WSDM ’21, page 553–561, New York, NY, US… find
  9. Xiaoxin He, Yijun Tian, Yifei Sun, Nitesh Chawla, Thomas Laurent, Yann LeCun, Xavier Bresson, and Bryan Hooi. 2024. G-retriever: Retrieval-augmented generation for textual graph understanding and question answering. Advances in Neural Information Processing Systems, 37:132876–132907.
  10. Xixin Hu, Xuan Wu, Yiheng Shu, and Yuzhong Qu. 2022. Logical form generation via multi-task learning for complex question answering over knowledge bases. In Proceedings of the 29th International Conference on Computational Linguistics, pages 1687– 1696, Gyeongju, Republic of Korea. International Com… find
  11. Xiang Huang, Sitao Cheng, Shanshan Huang, Jiayu Shen, Yong Xu, Chaoyun Zhang, and Yuzhong Qu. 2024. Queryagent: A reliable and efficient reasoning framework with environmental feedback based self-correction. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (… find
  12. Xiang Huang, Jiayu Shen, Shanshan Huang, Sitao Cheng, Xiaxia Wang, and Yuzhong Qu. 2025. TARGA: targeted synthetic data generation for practical reasoning over structured data. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 202… find
  13. Jinhao Jiang, Kun Zhou, Wayne Xin Zhao, Yang Song, Chen Zhu, Hengshu Zhu, and Ji-Rong Wen. 2025. KG-agent: An efficient autonomous agent framework for complex reasoning over knowledge graph. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Pa…
  14. Yunshi Lan, Gaole He, Jinhao Jiang, Jing Jiang, Wayne Xin Zhao, and Ji-Rong Wen. 2021. A survey on complex knowledge base question answering: Methods, challenges and solutions. In Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI 2021, Virtual Event / Mont… find
  15. Yunshi Lan, Gaole He, Jinhao Jiang, Jing Jiang, Wayne Xin Zhao, and Ji-Rong Wen. 2022. Complex knowledge base question answering: A survey. IEEE Transactions on Knowledge and Data Engineering, 35(11):11196–11215. find
  16. Bo Li, Tian Tian, Zhenghua Xu, Hao Cheng, Shikun Zhang, and Wei Ye. 2026a. Modeling uncertainty trends for timely retrieval in dynamic RAG. In Fortieth AAAI Conference on Artificial Intelligence, Thirty-Eighth Conference on Innovative Applications of Artificial Intelligence, Sixteenth Symposium on E… find
  17. Bo Li, Mingda Wang, Gexiang Fang, Shikun Zhang, and Wei Ye. 2026b. Retrieval as generation: A unified framework with self-triggered information planning. Preprint, arXiv:2604.11407.
  18. Tianle Li, Xueguang Ma, Alex Zhuang, Yu Gu, Yu Su, and Wenhu Chen. 2023. Few-shot in-context learning on knowledge base question answering. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2023, Toronto, Canada, July 9-14, 2023,… find
  19. Yading Li, Dandan Song, Changzhi Zhou, Yuhang Tian, Hao Wang, Ziyi Yang, and Shuhao Zhang. 2024a. A framework of knowledge graph-enhanced large language model based on question decomposition and atomic retrieval. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 11472–1… find
  20. Yading Li, Dandan Song, Changzhi Zhou, Yuhang Tian, Hao Wang, Ziyi Yang, and Shuhao Zhang. 2024b. A framework of knowledge graph-enhanced large language model based on question decomposition and atomic retrieval. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 11472–1… find
  21. Peiyang Liu. 2024. Unsupervised corrupt data detection for text training. Expert Systems with Applications, 248:123335. find
  22. Peiyang Liu, Xi Wang, Ziqiang Cui, and Wei Ye. 2025. Queries are not alone: Clustering text embeddings for video search. In Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval, pages 874– 883. find
  23. Peiyang Liu, Jinyu Yang, Lin Wang, Sen Wang, Yunlai Hao, and Huihui Bai. 2023. Retrieval-based unsupervised noisy label detection on text data. In Proceedings of the 32nd ACM International Conference on Information and Knowledge Management, pages 4099–4104. find
  24. Haoran Luo, Haihong E, Yikai Guo, Qika Lin, Xiaobao Wu, Xinyu Mu, Wenhao Liu, Meina Song, Yifan Zhu, and Anh Tuan Luu. 2025a. Kbqa-o1: Agentic knowledge base question answering with monte carlo tree search. In Forty-second International Conference on Machine Learning, ICML 2025, Vancouver, BC, Canad… find
  25. Haoran Luo, Haihong E, Zichen Tang, Shiyao Peng, Yikai Guo, Wentai Zhang, Chenghao Ma, Guanting Dong, Meina Song, Wei Lin, Yifan Zhu, and Anh Tuan Luu. 2024. Chatkbqa: A generate-then-retrieve framework for knowledge base question answering with fine-tuned large language models. In Findings of the A… find
  26. Linhao Luo, Zicheng Zhao, Gholamreza Haffari, Yuan-Fang Li, Chen Gong, and Shirui Pan. 2025b. Graph-constrained reasoning: Faithful reasoning on knowledge graphs with large language models. In Forty-second International Conference on Machine Learning, ICML 2025, Vancouver, BC, Canada, July 13-19, 20… find
  27. Costas Mavromatis and George Karypis. 2025. GNN-RAG: graph neural retrieval for efficient large language model reasoning on knowledge graphs. In Findings of the Association for Computational Linguistics, ACL 2025, Vienna, Austria, July 27 - August 1, 2025, pages 16682–16699. Association for Computat… find
  28. Zhijie Nie, Richong Zhang, Zhongyuan Wang, and Xudong Liu. 2024a. Code-style in-context learning for knowledge-based question answering. In Thirty-Eighth AAAI Conference on Artificial Intelligence, AAAI 2024, Thirty-Sixth Conference on Innovative Applications of Artificial Intelligence, IAAI 2024, F… find
  29. Zhijie Nie, Richong Zhang, Zhongyuan Wang, and Xudong Liu. 2024b. Code-style in-context learning for knowledge-based question answering. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 38, pages 18833–18841. find
  30. Jorge Pérez, Marcelo Arenas, and Claudio Gutierrez. 2009. Semantics and complexity of sparql. ACM Transactions on Database Systems (TODS), 34(3):1– 45. find
  31. Apoorv Saxena, Adrian Kochsiek, and Rainer Gemulla. 2022. Sequence-to-sequence knowledge graph completion and question answering. arXiv preprint arXiv:2203.10321. find
  32. Yiheng Shu, Zhiwei Yu, Yuhan Li, Börje F. Karlsson, Tingting Ma, Yuzhong Qu, and Chin-Yew Lin. 2022. TIARA: Multi-grained retrieval for robust question answering over large knowledge base. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 8108–8121, Abu… find
  33. Yu Su, Huan Sun, Brian Sadler, Mudhakar Srivatsa, Izzeddin Gür, Zenghui Yan, and Xifeng Yan. 2016. On generating characteristic-rich question sets for qa evaluation. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 562–572. find
  34. Yuan Sui, Yufei He, Nian Liu, Xiaoxin He, Kun Wang, and Bryan Hooi. 2025. Fidelis: Faithful reasoning in large language models for knowledge graph question answering. In Findings of the Association for Computational Linguistics, ACL 2025, Vienna, Austria, July 27 - August 1, 2025, pages 8315–8330. A… find
  35. Jiashuo Sun, Chengjin Xu, Lumingyuan Tang, Saizhuo Wang, Chen Lin, Yeyun Gong, Lionel M. Ni, Heung-Yeung Shum, and Jian Guo. 2024. Think-on-graph: Deep and responsible reasoning of large language model on knowledge graph. In The Twelfth International Conference on Learning Representations, ICLR 2024… find
  36. Yuhang Tian, Dandan Song, Zhijing Wu, Pan Yang, Changzhi Zhou, Jun Yang, Hao Wang, Huipeng Ma, Chenhao Li, and Luan Zhang. 2025. CompKBQA: Component-wise task decomposition for knowledge base question answering. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processin… find
  37. Yuhang Tian, Dandan Song, Zhijing Wu, Changzhi Zhou, Hao Wang, Jun Yang, Jing Xu, Ruanmin Cao, and Haoyu Wang. 2024. Augmenting reasoning capabilities of llms with graph structures in knowledge base question answering. In Findings of the Association for Computational Linguistics: EMNLP 2024, Miami,… find
  38. Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2022, Dublin, Ireland, May 22-27, 2022, pages 6032–6043. Association for Computational Linguistics. find
  39. Wen-tau Yih, Matthew Richardson, Christopher Meek, Ming-Wei Chang, and Jina Suh. 2016. The value of semantic parse labeling for knowledge base question answering. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 201–206.
  40. Donghan Yu, Sheng Zhang, Patrick Ng, Henghui Zhu, Alexander Hanbo Li, Jun Wang, Yiqun Hu, William Yang Wang, Zhiguo Wang, and Bing Xiang. 2023. Decaf: Joint decoding of answers and logical forms for question answering over knowledge bases. In The Eleventh International Conference on Learning Represe… find
  41. Lingxi Zhang, Jing Zhang, Yanling Wang, Shulin Cao, Xinmei Huang, Cuiping Li, Hong Chen, and Juanzi Li. 2023. FC-KBQA: A fine-to-coarse composition framework for knowledge base question answering. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: L… find
  42. Wayne Xin Zhao, Kun Zhou, Junyi Li, Tianyi Tang, Xiaolei Wang, Yupeng Hou, Yingqian Min, Beichen Zhang, Junjie Zhang, Zican Dong, and 1 others. 2023. A survey of large language models. arXiv preprint arXiv:2303.18223.
  43. Denny Vrandečić and Markus Krötzsch. 2014. Wikidata: a free collaborative knowledgebase. Communications of the ACM, 57(10):78–85.
  44. Guanming Xiong, Junwei Bao, and Wen Zhao. 2024. Interactive-kbqa: Multi-turn interactions for knowledge base question answering with large language models. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2024, Bangkok, Thailand,… find
  45. Guanming Xiong, Haochen Li, and Wen Zhao. 2025. Mcts-kbqa: Monte carlo tree search for knowledge base question answering. arXiv preprint arXiv:2502.13428. — [arXiv:2502.13428](https://arxiv.org/abs/2502.13428) find
  46. Xi Ye, Semih Yavuz, Kazuma Hashimoto, Yingbo Zhou, and Caiming Xiong. 2022. RNG-KBQA: generation augmented iterative ranking for knowledge base question answering. In Proceedings of the 60th Annual find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/tian-2026-subgraph-guided-executable-logical-form/