---
title: "Ontology-Guided Reverse Thinking Makes Large Language Models Stronger on Knowledge Graph — Liu 2025"
description: "The authors propose Ontology-Guided Reverse Thinking (ORT), a training-free, plug-and-play… 13.10 F1 on WebQSP. 30 references, cited by 8 papers here."
authors: ["Runxuan Liu", "Bei Luo", "Jiaqi Li", "Baoxin Wang", "Ming Liu", "Dayong Wu", "Shijin Wang", "Bing Qin"]
year: 2025
venue: "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)"
source: "https://aclanthology.org/2025.acl-long.741/"
doi: "10.18653/v1/2025.acl-long.741"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/liu-2025-ontology-guided-reverse-thinking-makes/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/liu-2025-ontology-guided-reverse-thinking-makes/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2025](https://md.research.elamur.ai/free/en/papers/2025/) / Ontology-Guided Reverse Thinking Makes Large Language Models Stronger on Knowledge Graph Question Answering

# Ontology-Guided Reverse Thinking Makes Large Language Models Stronger on Knowledge Graph Question Answering

**Authors:** Runxuan Liu, Bei Luo, [Jiaqi Li](https://md.research.elamur.ai/free/en/authors/jiaqi-li/), Baoxin Wang, Ming Liu, Dayong Wu, [Shijin Wang](https://md.research.elamur.ai/free/en/authors/shijin-wang/) and [Bing Qin](https://md.research.elamur.ai/free/en/authors/bing-qin/) · **Year:** 2025 · **Venue:** Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2025.acl-long.741/) · [PDF](https://aclanthology.org/2025.acl-long.741.pdf) · [DOI 10.18653/v1/2025.acl-long.741](https://doi.org/10.18653/v1/2025.acl-long.741) · [OpenAlex](https://openalex.org/W4412945188)

**Citations:** 7 citations (OpenAlex, 2026-10-14) · 8 in our library, of the 140,884 papers whose bibliographies we read

## Summary
Approaches that couple large language models with knowledge graphs for question answering (KGQA) typically locate relevant facts through entity embeddings and graph search. This breaks down when the question asks for a concept rather than a named entity. For example, a "stadium" has no direct counterpart node, so the search never reaches the answer. The authors propose Ontology-Guided Reverse Thinking (ORT), a training-free, plug-and-play framework that works backwards from what the question seeks to what it already provides.

First, an LLM tags the condition entities and the aim of the question with labels drawn from the KG's label list. ORT then grows a tree over the KG ontology, rooted at the aim labels. It prunes branches that lack condition labels and removes cycles, which yields abstract label reasoning paths. These paths steer retrieval of concrete entity paths, and the LLM summarizes those into an answer.

On WebQSP and CWQ, ORT reaches state-of-the-art results among the compared systems. This shows that exploiting ontology structure can improve LLM-based KGQA without fine-tuning.

## Key points
- **Three-stage pipeline:**
  - condition and aim recognition, with the LLM choosing labels from the KG's label list;
  - reverse reasoning on the ontology, which involves building a neighbor-label dictionary, expanding a tree from the aim labels up to a hop limit (max_pop), pruning by conditions, pruning cycles, and filtering paths semantically with the LLM;
  - guided answer mining over the retrieved entity paths.
- **Main results:** ORT scores Hit@1 89.43 / F1 71.83 on WebQSP and Hit@1 72.91 / F1 62.63 on CWQ.
- **Gain over direct answering:** compared with the LLM answering on its own, ORT improves Hit@1 by at least 25.43% and F1 by at least 25.82%.
- **Trace Forward ablation:** a variant that reasons forward from the conditions performs worse, losing 11.61 Hit@1 and 13.10 F1 on WebQSP and 12.18 Hit@1 and 13.33 F1 on CWQ. It still beats MindMap.
- **Other ablations:** removing the LLM path filter raises Recall and F1 on WebQSP but lowers Hit@1 and Precision; the authors keep the filter to limit hallucinations. Removing rule-guided abstract paths altogether causes a sharp drop. Acknowledged limitations are the many entities that can satisfy label constraints and noisy entity paths passed to the LLM.

*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: [Natural language processing](https://md.research.elamur.ai/free/en/shelves/nlp/)

Topics: [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · [❓ Question answering](https://md.research.elamur.ai/free/en/topics/question-answering/) · [🕸️ Knowledge graphs & ontologies](https://md.research.elamur.ai/free/en/topics/knowledge-graphs/)

## Institutions

- [University of Science and Technology of China](https://md.research.elamur.ai/free/en/universities/university-of-science-and-technology-of-china/) — University, Hefei, China · 18 works · 109,489 citations
- [Harbin Institute of Technology](https://md.research.elamur.ai/free/en/universities/harbin-institute-of-technology/) — University, Harbin, China · 58 works · 25,250 citations
- [IFlyTek](https://md.research.elamur.ai/free/en/companies/iflytek/) — Company, Hefei · 6 works · 2,381 citations
- [Peng Cheng Laboratory](https://md.research.elamur.ai/free/en/labs/peng-cheng-laboratory/) — Research institute, Shenzhen, China · 12 works · 1,659 citations

## Cite

Cite as: Runxuan Liu, Bei Luo, Jiaqi Li, Baoxin Wang, Ming Liu, Dayong Wu, Shijin Wang and Bing Qin. 2025. Ontology-Guided Reverse Thinking Makes Large Language Models Stronger on Knowledge Graph Question Answering. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{liu2025ontology,
  title = {{Ontology-Guided Reverse Thinking Makes Large Language Models Stronger on Knowledge Graph Question Answering}},
  author = {Runxuan Liu, Bei Luo, Jiaqi Li, Baoxin Wang, Ming Liu, Dayong Wu, Shijin Wang and Bing Qin},
  booktitle = {Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2025},
  doi = {10.18653/v1/2025.acl-long.741},
  url = {https://doi.org/10.18653/v1/2025.acl-long.741}
}
```

- [← previous METAL: A Multi-Agent Framework for Chart Generation with Test-Time Scaling](https://md.research.elamur.ai/free/en/papers/li-2025-metal-multi-agent-framework-chart/)
- [next → Comparative Study of Multilingual Idioms and Similes in Large Language Models](https://md.research.elamur.ai/free/en/papers/khoshtab-2025-comparative-study-multilingual-idioms-similes/)
- [↑ back to papers of 2025](https://md.research.elamur.ai/free/en/papers/2025/)

## References

30 references, 4 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Lochan Basyal and Mihir Sanghvi. 2023. Text summarization using large language models: A comparative study of mpt-7b-instruct, falcon-7b-instruct, and openai chat-gpt models. ArXiv, abs/2310.10449. — [arXiv:2310.10449](https://arxiv.org/abs/2310.10449) [find](https://scholar.google.com/scholar?q=Lochan+Basyal+and+Mihir+Sanghvi%2E+2023%2E+Text+summarization+using+large+language+models%3A+A+comparative+study+of+mpt%2D7b%2Dinstruct%2C+falcon%2D7b%2Dinstruct%2C+and+openai+chat%2Dgpt+models%2E+ArXiv%2C+abs%2F2310%2E10449%2E+%E2%80%94+)
2. Kurt D. Bollacker, Colin Evans, Praveen K. Paritosh, Tim Sturge, and Jamie Taylor. 2008. Freebase: a collaboratively created graph database for structuring human knowledge. In SIGMOD Conference. [find](https://scholar.google.com/scholar?q=Kurt+D%2E+Bollacker%2C+Colin+Evans%2C+Praveen+K%2E+Paritosh%2C+Tim+Sturge%2C+and+Jamie+Taylor%2E+2008%2E+Freebase%3A+a+collaboratively+created+graph+database+for+structuring+human+knowledge%2E+In+SIGMOD+Conference%2E)
3. Yihan Cao, Yanbin Kang, Chi Wang, and Lichao Sun. 2023. Instruction mining: Instruction data selection for tuning large language models. [find](https://scholar.google.com/scholar?q=Yihan+Cao%2C+Yanbin+Kang%2C+Chi+Wang%2C+and+Lichao+Sun%2E+2023%2E+Instruction+mining%3A+Instruction+data+selection+for+tuning+large+language+models%2E)
4. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. Bert: Pre-training of deep bidirectional transformers for language understanding. In North American Chapter of the Association for Computational Linguistics. [our card](https://md.research.elamur.ai/free/en/papers/devlin-2019-bert-pre-training-deep-bidirectional/)
5. 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. Proceedings of the 14th ACM International Conference on Web Search and Data Mining. [find](https://scholar.google.com/scholar?q=Gaole+He%2C+Yunshi+Lan%2C+Jing+Jiang%2C+Wayne+Xin+Zhao%2C+and+Ji+rong+Wen%2E+2021%2E+Improving+multi%2Dhop+knowledge+base+question+answering+by+learning+intermediate+supervision+signals%2E+Proceedings+of+the+14th+ACM)
6. Yuchen Hu, Chen Chen, Chao-Han Yang, Ruizhe Li, Dong Zhang, Zhehuai Chen, and EngSiong Chng. 2024a. GenTranslate: Large language models are generative multilingual speech and machine translators. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Lo… [find](https://scholar.google.com/scholar?q=Yuchen+Hu%2C+Chen+Chen%2C+Chao%2DHan+Yang%2C+Ruizhe+Li%2C+Dong+Zhang%2C+Zhehuai+Chen%2C+and+EngSiong+Chng%2E+2024a%2E+GenTranslate%3A+Large+language+models+are+generative+multilingual+speech+and+machine+translators%2E+In+P)
7. Yuntong Hu, Zhihan Lei, Zhengwu Zhang, Bo Pan, Chen Ling, and Liang Zhao. 2024b. Grag: Graph retrieval-augmented generation. ArXiv, abs/2405.16506. [find](https://scholar.google.com/scholar?q=Yuntong+Hu%2C+Zhihan+Lei%2C+Zhengwu+Zhang%2C+Bo+Pan%2C+Chen+Ling%2C+and+Liang+Zhao%2E+2024b%2E+Grag%3A+Graph+retrieval%2Daugmented+generation%2E+ArXiv%2C+abs%2F2405%2E16506%2E)
8. Jinhao Jiang, Kun Zhou, Wayne Xin Zhao, and Ji rong Wen. 2022. Unikgqa: Unified retrieval and reasoning for solving multi-hop question answering over knowledge graph. ArXiv, abs/2212.00959. [find](https://scholar.google.com/scholar?q=Jinhao+Jiang%2C+Kun+Zhou%2C+Wayne+Xin+Zhao%2C+and+Ji+rong+Wen%2E+2022%2E+Unikgqa%3A+Unified+retrieval+and+reasoning+for+solving+multi%2Dhop+question+answering+over+knowledge+graph%2E+ArXiv%2C+abs%2F2212%2E00959%2E)
9. Pengcheng Jiang, Lang Cao, Cao Xiao, Parminder Bhatia, Jimeng Sun, and Jiawei Han. 2024. Kg-fit: Knowledge graph fine-tuning upon open-world knowledge. ArXiv, abs/2405.16412. — [arXiv:2405.16412](https://arxiv.org/abs/2405.16412) [find](https://scholar.google.com/scholar?q=Pengcheng+Jiang%2C+Lang+Cao%2C+Cao+Xiao%2C+Parminder+Bhatia%2C+Jimeng+Sun%2C+and+Jiawei+Han%2E+2024%2E+Kg%2Dfit%3A+Knowledge+graph+fine%2Dtuning+upon+open%2Dworld+knowledge%2E+ArXiv%2C+abs%2F2405%2E16412%2E+%E2%80%94+%5BarXiv%3A2405%2E16412%5D%28http)
10. Mufei Li, Siqi Miao, and Pan Li. 2024. Simple is effective: The roles of graphs and large language models in knowledge-graph-based retrieval-augmented generation. ArXiv, abs/2410.20724. — [arXiv:2410.20724](https://arxiv.org/abs/2410.20724) [find](https://scholar.google.com/scholar?q=Mufei+Li%2C+Siqi+Miao%2C+and+Pan+Li%2E+2024%2E+Simple+is+effective%3A+The+roles+of+graphs+and+large+language+models+in+knowledge%2Dgraph%2Dbased+retrieval%2Daugmented+generation%2E+ArXiv%2C+abs%2F2410%2E20724%2E+%E2%80%94+%5BarXiv%3A2410%2E)
11. Yunxin Li, Zhenyu Liu, Zitao Li, Xuanyu Zhang, Zhenran Xu, Xinyu Chen, Haoyuan Shi, Shenyuan Jiang, Xintong Wang, Jifang Wang, Shouzheng Huang, Xinping Zhao, Borui Jiang, Lanqing Hong, Longyue Wang, Zhuotao Tian, Baoxing Huai, Wenhan Luo, Weihua Luo, Zheng Zhang, Baotian Hu, and Min Zhang. 2025. Per… — [arXiv:2505.04921](https://arxiv.org/abs/2505.04921) [find](https://scholar.google.com/scholar?q=Yunxin+Li%2C+Zhenyu+Liu%2C+Zitao+Li%2C+Xuanyu+Zhang%2C+Zhenran+Xu%2C+Xinyu+Chen%2C+Haoyuan+Shi%2C+Shenyuan+Jiang%2C+Xintong+Wang%2C+Jifang+Wang%2C+Shouzheng+Huang%2C+Xinping+Zhao%2C+Borui+Jiang%2C+Lanqing+Hong%2C+Longyue+Wang%2C+Z)
12. Linhao Luo, Yuan-Fang Li, Gholamreza Haffari, and Shirui Pan. 2024. Reasoning on graphs: Faithful and interpretable large language model reasoning. International Conference on Learning Representations, abs/2310.01061. [find](https://scholar.google.com/scholar?q=Linhao+Luo%2C+Yuan%2DFang+Li%2C+Gholamreza+Haffari%2C+and+Shirui+Pan%2E+2024%2E+Reasoning+on+graphs%3A+Faithful+and+interpretable+large+language+model+reasoning%2E+International+Conference+on+Learning+Representations)
13. Alexander H. Miller, Adam Fisch, Jesse Dodge, Amir-Hossein Karimi, Antoine Bordes, and Jason Weston. 2016. Key-value memory networks for directly reading documents. ArXiv, abs/1606.03126. [find](https://scholar.google.com/scholar?q=Alexander+H%2E+Miller%2C+Adam+Fisch%2C+Jesse+Dodge%2C+Amir%2DHossein+Karimi%2C+Antoine+Bordes%2C+and+Jason+Weston%2E+2016%2E+Key%2Dvalue+memory+networks+for+directly+reading+documents%2E+ArXiv%2C+abs%2F1606%2E03126%2E)
14. Mohaimenul Azam Khan Raiaan, Md. Saddam Hossain Mukta, Kaniz Fatema, Nur Mohammad Fahad, Sad-man Sakib, Most. Marufatul Jannat Mim, Jubaer Ahmad, Mohammed Eunus Ali, and Sami Azam. 2024. A review on large language models: Architectures, applications, taxonomies, open issues and challenges. IEEE Acce… [find](https://scholar.google.com/scholar?q=Mohaimenul+Azam+Khan+Raiaan%2C+Md%2E+Saddam+Hossain+Mukta%2C+Kaniz+Fatema%2C+Nur+Mohammad+Fahad%2C+Sad%2Dman+Sakib%2C+Most%2E+Marufatul+Jannat+Mim%2C+Jubaer+Ahmad%2C+Mohammed+Eunus+Ali%2C+and+Sami+Azam%2E+2024%2E+A+review+on+l)
15. Jocelyn Shen, Joel Mire, Hae Won Park, Cynthia Breazeal, and Maarten Sap. 2024. HEART-felt narratives: Tracing empathy and narrative style in personal stories with LLMs. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 1026–1046, Miami, Florida, USA. A… [find](https://scholar.google.com/scholar?q=Jocelyn+Shen%2C+Joel+Mire%2C+Hae+Won+Park%2C+Cynthia+Breazeal%2C+and+Maarten+Sap%2E+2024%2E+HEART%2Dfelt+narratives%3A+Tracing+empathy+and+narrative+style+in+personal+stories+with+LLMs%2E+In+Proceedings+of+the+2024+Con)
16. Haitian Sun, Bhuwan Dhingra, Manzil Zaheer, Kathryn Mazaitis, Ruslan Salakhutdinov, and William W. Cohen. 2018. Open domain question answering using early fusion of knowledge bases and text. ArXiv, abs/1809.00782. [find](https://scholar.google.com/scholar?q=Haitian+Sun%2C+Bhuwan+Dhingra%2C+Manzil+Zaheer%2C+Kathryn+Mazaitis%2C+Ruslan+Salakhutdinov%2C+and+William+W%2E+Cohen%2E+2018%2E+Open+domain+question+answering+using+early+fusion+of+knowledge+bases+and+text%2E+ArXiv%2C+ab)
17. Jiashuo Sun, Chengjin Xu, Lumingyuan Tang, Sai Wang, Chen Lin, Yeyun Gong, Heung yeung Shum, and Jian Guo. 2023. Think-on-graph: Deep and responsible reasoning of large language model with knowledge graph. ArXiv, abs/2307.07697. [find](https://scholar.google.com/scholar?q=Jiashuo+Sun%2C+Chengjin+Xu%2C+Lumingyuan+Tang%2C+Sai+Wang%2C+Chen+Lin%2C+Yeyun+Gong%2C+Heung+yeung+Shum%2C+and+Jian+Guo%2E+2023%2E+Think%2Don%2Dgraph%3A+Deep+and+responsible+reasoning+of+large+language+model+with+knowledge+g)
18. Alon Talmor and Jonathan Berant. 2018. The web as a knowledge-base for answering complex questions. ArXiv, abs/1803.06643. [our card](https://md.research.elamur.ai/free/en/papers/talmor-2018-web-as-knowledge-base-answering/)
19. Xingyu Tan, Xiaoyang Wang, Qing Liu, Xiwei Xu, Xin Yuan, and Wenjie Zhang. 2024. Paths-over-graph: Knowledge graph empowered large language model reasoning. ArXiv, abs/2410.14211. [find](https://scholar.google.com/scholar?q=Xingyu+Tan%2C+Xiaoyang+Wang%2C+Qing+Liu%2C+Xiwei+Xu%2C+Xin+Yuan%2C+and+Wenjie+Zhang%2E+2024%2E+Paths%2Dover%2Dgraph%3A+Knowledge+graph+empowered+large+language+model+reasoning%2E+ArXiv%2C+abs%2F2410%2E14211%2E)
20. 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 Annual Meeting of the Association for Computational Linguistics. [our card](https://md.research.elamur.ai/free/en/papers/yih-2016-value-semantic-parse-labeling-knowledge/)
21. Xiong. 2023. Knowledge-driven cot: Exploring faithful reasoning in llms for knowledge-intensive question answering. ArXiv, abs/2308.13259. — [arXiv:2308.13259](https://arxiv.org/abs/2308.13259) [find](https://scholar.google.com/scholar?q=Xiong%2E+2023%2E+Knowledge%2Ddriven+cot%3A+Exploring+faithful+reasoning+in+llms+for+knowledge%2Dintensive+question+answering%2E+ArXiv%2C+abs%2F2308%2E13259%2E+%E2%80%94+%5BarXiv%3A2308%2E13259%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2308%2E13259%29)
22. Yilin Wen, Zifeng Wang, and Jimeng Sun. 2024. MindMap: Knowledge graph prompting sparks graph of thoughts in large language models. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 10370–10388, Bangkok, Thailand. Association fo… [find](https://scholar.google.com/scholar?q=Yilin+Wen%2C+Zifeng+Wang%2C+and+Jimeng+Sun%2E+2024%2E+MindMap%3A+Knowledge+graph+prompting+sparks+graph+of+thoughts+in+large+language+models%2E+In+Proceedings+of+the+62nd+Annual+Meeting+of+the+Association+for+Com)
23. Dayong Wu, Jiaqi Li, Baoxin Wang, Honghong Zhao, Siyuan Xue, Yanjie Yang, Zhijun Chang, Rui Zhang, Li Qian, Bo Wang, Shijin Wang, Zhixiong Zhang, and Guoping Hu. 2024a. Sparkra: A retrieval-augmented knowledge service system based on spark large language model. ArXiv, abs/2408.06574. [find](https://scholar.google.com/scholar?q=Dayong+Wu%2C+Jiaqi+Li%2C+Baoxin+Wang%2C+Honghong+Zhao%2C+Siyuan+Xue%2C+Yanjie+Yang%2C+Zhijun+Chang%2C+Rui+Zhang%2C+Li+Qian%2C+Bo+Wang%2C+Shijin+Wang%2C+Zhixiong+Zhang%2C+and+Guoping+Hu%2E+2024a%2E+Sparkra%3A+A+retrieval%2Daugmented+)
24. Junde Wu, Jiayuan Zhu, and Yunli Qi. 2024b. Medical graph rag: Towards safe medical large language model via graph retrieval-augmented generation. ArXiv, abs/2408.04187. — [arXiv:2408.04187](https://arxiv.org/abs/2408.04187) [find](https://scholar.google.com/scholar?q=Junde+Wu%2C+Jiayuan+Zhu%2C+and+Yunli+Qi%2E+2024b%2E+Medical+graph+rag%3A+Towards+safe+medical+large+language+model+via+graph+retrieval%2Daugmented+generation%2E+ArXiv%2C+abs%2F2408%2E04187%2E+%E2%80%94+%5BarXiv%3A2408%2E04187%5D%28https%3A%2F%2Fa)
25. Donghan Yu, Shenmin Zhang, Patrick Ng, Henghui Zhu, Alexander Hanbo Li, J. Wang, Yiqun Hu, William Wang, Zhiguo Wang, and Bing Xiang. 2022. Decaf: Joint decoding of answers and logical forms for question answering over knowledge bases. ArXiv, abs/2210.00063. [find](https://scholar.google.com/scholar?q=Donghan+Yu%2C+Shenmin+Zhang%2C+Patrick+Ng%2C+Henghui+Zhu%2C+Alexander+Hanbo+Li%2C+J%2E+Wang%2C+Yiqun+Hu%2C+William+Wang%2C+Zhiguo+Wang%2C+and+Bing+Xiang%2E+2022%2E+Decaf%3A+Joint+decoding+of+answers+and+logical+forms+for+quest)
26. Jing Zhang, Xiaokang Zhang, Jifan Yu, Jian Tang, Jie Tang, Cuiping Li, and Hong Chen. 2022. Subgraph retrieval enhanced model for multi-hop knowledge base question answering. In Annual Meeting of the Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Jing+Zhang%2C+Xiaokang+Zhang%2C+Jifan+Yu%2C+Jian+Tang%2C+Jie+Tang%2C+Cuiping+Li%2C+and+Hong+Chen%2E+2022%2E+Subgraph+retrieval+enhanced+model+for+multi%2Dhop+knowledge+base+question+answering%2E+In+Annual+Meeting+of+the+)
27. Yizhe Zhang, Siqi Sun, Michel Galley, Yen-Chun Chen, Chris Brockett, Xiang Gao, Jianfeng Gao, Jingjing Liu, and William B. Dolan. 2019. Dialogpt : Large-scale generative pre-training for conversational response generation. In Annual Meeting of the Association for Computational Linguistics. [our card](https://md.research.elamur.ai/free/en/papers/zhang-2019-dialogpt-large-scale-generative-pre/)
28. Sincy V. Thambi and P. C. Reghuraj. 2022. Towards improving the performance of question answering system using knowledge graph - a survey. 2022 Second International Conference on Artificial Intelligence and Smart Energy (ICAIS), pages 672–679. [find](https://scholar.google.com/scholar?q=Sincy+V%2E+Thambi+and+P%2E+C%2E+Reghuraj%2E+2022%2E+Towards+improving+the+performance+of+question+answering+system+using+knowledge+graph+%2D+a+survey%2E+2022+Second+International+Conference+on+Artificial+Intelligen)
29. Junjie Wang, Mingyang Chen, Binbin Hu, Dan Yang, Ziqi Liu, Yue Shen, Peng Wei, Zhiqiang Zhang, Jinjie Gu, Jun Zhou, Jeff Z. Pan, Wen Zhang, and Huajun Chen. 2024. Learning to plan for retrieval-augmented large language models from knowledge graphs. In Findings of the Association for Computational Li… [find](https://scholar.google.com/scholar?q=Junjie+Wang%2C+Mingyang+Chen%2C+Binbin+Hu%2C+Dan+Yang%2C+Ziqi+Liu%2C+Yue+Shen%2C+Peng+Wei%2C+Zhiqiang+Zhang%2C+Jinjie+Gu%2C+Jun+Zhou%2C+Jeff+Z%2E+Pan%2C+Wen+Zhang%2C+and+Huajun+Chen%2E+2024%2E+Learning+to+plan+for+retrieval%2Daugmen)
30. Keheng Wang, Feiyu Duan, Sirui Wang, Peiguang Li, Yunsen Xian, Chuantao Yin, Wenge Rong, and Zhang [find](https://scholar.google.com/scholar?q=Keheng+Wang%2C+Feiyu+Duan%2C+Sirui+Wang%2C+Peiguang+Li%2C+Yunsen+Xian%2C+Chuantao+Yin%2C+Wenge+Rong%2C+and+Zhang)