---
title: "COSMOS — paper by Peng et al. (2026) — summary and ideas"
description: "The paper tackles evidence retrieval for Knowledge Base Question Answering (KBQA), where an LLM needs a compact and… 61 references."
authors: ["Boci Peng", "Xiao Liu", "Boren Hu", "Yun Zhu", "Xuanbo Fan", "Yanwei Yue", "Chunyu Yang", "Yan Zhang"]
year: 2026
venue: "Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)"
source: "https://aclanthology.org/2026.acl-long.1662/"
doi: "10.18653/v1/2026.acl-long.1662"
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/peng-2026-cosmos-connectivity-oriented-submodular-maximization/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/peng-2026-cosmos-connectivity-oriented-submodular-maximization/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/26/) / COSMOS: Connectivity-Oriented Submodular Maximization for Optimal Subgraph Retrieval

# COSMOS: Connectivity-Oriented Submodular Maximization for Optimal Subgraph Retrieval

**Authors:** [Boci Peng](https://md.research.elamur.ai/free/en/authors/boci-peng/), [Xiao Liu](https://md.research.elamur.ai/free/en/authors/xiao-liu/), Boren Hu, [Yun Zhu](https://md.research.elamur.ai/free/en/authors/yun-zhu/), [Xuanbo Fan](https://md.research.elamur.ai/free/en/authors/xuanbo-fan/), [Yanwei Yue](https://md.research.elamur.ai/free/en/authors/yanwei-yue/), Chunyu Yang and [Yan Zhang](https://md.research.elamur.ai/free/en/authors/yan-zhang/) · **Year:** 2026 · **Venue:** [Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)](https://md.research.elamur.ai/free/en/venues/acl/) ([ACL 2026](https://md.research.elamur.ai/free/en/venues/acl/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.acl-long.1662/) · [PDF](https://aclanthology.org/2026.acl-long.1662.pdf) · [DOI 10.18653/v1/2026.acl-long.1662](https://doi.org/10.18653/v1/2026.acl-long.1662) · [OpenAlex](https://openalex.org/W7166834870)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary

The paper tackles evidence retrieval for Knowledge Base Question Answering (KBQA), where an LLM needs a compact and *connected* set of knowledge-graph facts rather than isolated triplets. The authors identify weaknesses in three existing families of retrievers:

- **Embedding retrievers** ignore graph structure.
- **Heuristic graph algorithms** lean toward short, generic paths.
- **Iterative LLM search agents** are slow and get stuck in local optima.

COSMOS recasts retrieval as maximizing a submodular utility over edges, subject to three constraints: a size budget, subgraph connectivity, and inclusion of the query entities. Because the exact problem is NP-hard, the method solves it in two stages:

1. It grows high-value clusters around seed entities greedily.
2. It joins the separate clusters through a Maximum Spanning Tree over a semantic meta-graph.

Each stage comes with an approximation guarantee. A contrastive fine-tuning step then adapts the triplet encoder to the KG topology. On WebQSP, CWQ and M3GQA, COSMOS reports state-of-the-art results. This suggests that principled, structure-aware retrieval can improve LLM grounding without the cost of repeated LLM calls.

## Key points

- **Utility function:** a monotone Maximal Marginal Relevance (MMR) score with a weight λ. It rewards cosine similarity between a triplet and the query and penalizes overlap with triplets already selected.
- **Pipeline:** Seed-Guided Greedy Expansion, then Topology-Aware Component Aggregation, which uses MaxST with PPR-based bridge candidates. Structure-Aware Contrastive Tuning uses an InfoNCE loss with hard and easy negatives.
- **Budget:** triplet budgets K ∈ {50, 100, 200, 300} were tested. Recall rises sharply from 50 to 100 and then levels off, and F1 on WebQSP dips slightly at 300. K = 100 is used as the default.
- **Backbones:** GPT-4o consistently outperforms GPT-4o-mini.
- **Transfer tuning:** training the encoder on the union of datasets gives the best results. As reconstructed from the extracted table, Hit/F1 reach about 92.6/78.5 on WebQSP and 66.1/56.3 on CWQ. Cross-dataset tuning loses only a few points. Limitations noted by the authors include English-only evaluation and reliance on QA pairs for tuning.

*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

- [Peking University](https://md.research.elamur.ai/free/en/universities/peking-university/) — University, Beijing, China · 244 works · 39,359 citations
- [Shanghai Artificial Intelligence Laboratory](https://md.research.elamur.ai/free/en/labs/shanghai-artificial-intelligence-laboratory/) — Research institute, Shanghai, China · 117 works · 11,281 citations
- [University of Macau](https://md.research.elamur.ai/free/en/universities/university-of-macau/) — University, Macao, China · 33 works · 2,223 citations

📚 Shelves (7): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 2,869 works · [⚛️ Physics and Astronomy](https://md.research.elamur.ai/free/en/shelves/physics-and-astronomy/) · 44 works · [⚛️ Statistical and Nonlinear Physics](https://md.research.elamur.ai/free/en/shelves/physics-and-astronomy/statistical-and-nonlinear-physics/) · 40 works

🧭 Topics (1): [🔍 Information retrieval & search](https://md.research.elamur.ai/free/en/topics/information-retrieval/) · 473 works

## Cite

Cite as: Boci Peng, Xiao Liu, Boren Hu, Yun Zhu, Xuanbo Fan, Yanwei Yue, Chunyu Yang and Yan Zhang. 2026. COSMOS: Connectivity-Oriented Submodular Maximization for Optimal Subgraph Retrieval. Proceedings of the 64th 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{peng2026cosmos,
  title = {{COSMOS: Connectivity-Oriented Submodular Maximization for Optimal Subgraph Retrieval}},
  author = {Boci Peng, Xiao Liu, Boren Hu, Yun Zhu, Xuanbo Fan, Yanwei Yue, Chunyu Yang and Yan Zhang},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-long.1662},
  url = {https://doi.org/10.18653/v1/2026.acl-long.1662}
}
```

- [← previous CorSpell: Introducing a Semiautomatic Tool for Spelling Normalization in Brazilian Portuguese](https://md.research.elamur.ai/free/en/papers/schoffen-2026-corspell-introducing-semiautomatic-tool-spelling/)
- [next → CoTEvol: Self-Evolving Chain-of-Thoughts for Data Synthesis in Mathematical Reasoning](https://md.research.elamur.ai/free/en/papers/wang-2026-cotevol-self-evolving-chain-thoughts/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/26/)

## References

61 references, 15 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Jinheon Baek, Alham Fikri Aji, Jens Lehmann, and Sung Ju Hwang. 2023a. Direct fact retrieval from knowledge graphs without entity linking. 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, p… [find](https://scholar.google.com/scholar?q=Jinheon+Baek%2C+Alham+Fikri+Aji%2C+Jens+Lehmann%2C+and+Sung+Ju+Hwang%2E+2023a%2E+Direct+fact+retrieval+from+knowledge+graphs+without+entity+linking%2E+In+Proceedings+of+the+61st+Annual+Meeting+of+the+Association+)
2. Jinheon Baek, Alham Fikri Aji, and Amir Saffari. 2023b. [Knowledge-augmented language model prompting for zero-shot knowledge graph question answering](https://md.research.elamur.ai/free/en/papers/baek-2023-knowledge-augmented-language-model-prompting/).
3. 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 Proceedings of the ACM SIG-MOD International Conference on Management of Data, SIGMOD 2008, Vancouver, BC, Canada, June 10-1… [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+Proceedings+of+the+ACM+S)
4. Antoine Bordes, Nicolas Usunier, Sumit Chopra, and Jason Weston. 2015. Large-scale simple question answering with memory networks. [find](https://scholar.google.com/scholar?q=Antoine+Bordes%2C+Nicolas+Usunier%2C+Sumit+Chopra%2C+and+Jason+Weston%2E+2015%2E+Large%2Dscale+simple+question+answering+with+memory+networks%2E)
5. Linbo Cao and Jinman Zhao. 2025. Pretraining on the test set is no longer all you need: A debate-driven approach to QA benchmarks. In Second Conference on Language Modeling. [find](https://scholar.google.com/scholar?q=Linbo+Cao+and+Jinman+Zhao%2E+2025%2E+Pretraining+on+the+test+set+is+no+longer+all+you+need%3A+A+debate%2Ddriven+approach+to+QA+benchmarks%2E+In+Second+Conference+on+Language+Modeling%2E)
6. Abhimanyu Das and David Kempe. 2011. Submodular meets spectral: Greedy algorithms for subset selection, sparse approximation and dictionary selection. In Proceedings of the 28th International Conference on Machine Learning, ICML 2011, Bellevue, Washington, USA, June 28 - July 2, 2011, pages 1057–106… [find](https://scholar.google.com/scholar?q=Abhimanyu+Das+and+David+Kempe%2E+2011%2E+Submodular+meets+spectral%3A+Greedy+algorithms+for+subset+selection%2C+sparse+approximation+and+dictionary+selection%2E+In+Proceedings+of+the+28th+International+Conferen)
7. Mohammad Dehghan, Mohammad Ali Alomrani, Sunyam Bagga, David Alfonso-Hermelo, Khalil Bibi, Abbas Ghaddar, Yingxue Zhang, Xiaoguang Li, Jianye Hao, Qun Liu, Jimmy Lin, Boxing Chen, Prasanna Parthasarathi, Mahdi Biparva, and Mehdi Rezagholizadeh. 2024. EWEK-QA : Enhanced web and efficient knowledge gr… [find](https://scholar.google.com/scholar?q=Mohammad+Dehghan%2C+Mohammad+Ali+Alomrani%2C+Sunyam+Bagga%2C+David+Alfonso%2DHermelo%2C+Khalil+Bibi%2C+Abbas+Ghaddar%2C+Yingxue+Zhang%2C+Xiaoguang+Li%2C+Jianye+Hao%2C+Qun+Liu%2C+Jimmy+Lin%2C+Boxing+Chen%2C+Prasanna+Parthasarat)
8. Guanting Dong, Rumei Li, Sirui Wang, Yupeng Zhang, Yunsen Xian, and Weiran Xu. 2023. Bridging the kb-text gap: Leveraging structured knowledge-aware pre-training for KBQA. In Proceedings of the 32nd ACM International Conference on Information and Knowledge Management, CIKM 2023, Birmingham, United K… [find](https://scholar.google.com/scholar?q=Guanting+Dong%2C+Rumei+Li%2C+Sirui+Wang%2C+Yupeng+Zhang%2C+Yunsen+Xian%2C+and+Weiran+Xu%2E+2023%2E+Bridging+the+kb%2Dtext+gap%3A+Leveraging+structured+knowledge%2Daware+pre%2Dtraining+for+KBQA%2E+In+Proceedings+of+the+32nd+A)
9. Wenqi Fan, Yujuan Ding, Liangbo Ning, Shijie Wang, Hengyun Li, Dawei Yin, Tat-Seng Chua, and Qing Li. 2024. [A survey on RAG meeting llms: Towards retrieval-augmented large language models](https://md.research.elamur.ai/free/en/papers/fan-2024-survey-rag-meeting-llms-towards/). In Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2024, Barcelona, S…
10. Nicholas Frosst, Nicolas Papernot, and Geoffrey E. Hinton. 2019. Analyzing and improving representations with the soft nearest neighbor loss. In Proceedings of the 36th International Conference on Machine Learning, ICML 2019, 9-15 June 2019, Long Beach, California, USA, pages 2012–2020. [find](https://scholar.google.com/scholar?q=Nicholas+Frosst%2C+Nicolas+Papernot%2C+and+Geoffrey+E%2E+Hinton%2E+2019%2E+Analyzing+and+improving+representations+with+the+soft+nearest+neighbor+loss%2E+In+Proceedings+of+the+36th+International+Conference+on+Mac)
11. Tiezheng Guo, Qingwen Yang, Chen Wang, Yanyi Liu, Pan Li, Jiawei Tang, Dapeng Li, and Yingyou Wen. 2024. Knowledgenavigator: Leveraging large language models for enhanced reasoning over knowledge graph. [find](https://scholar.google.com/scholar?q=Tiezheng+Guo%2C+Qingwen+Yang%2C+Chen+Wang%2C+Yanyi+Liu%2C+Pan+Li%2C+Jiawei+Tang%2C+Dapeng+Li%2C+and+Yingyou+Wen%2E+2024%2E+Knowledgenavigator%3A+Leveraging+large+language+models+for+enhanced+reasoning+over+knowledge+grap)
12. 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 WSDM ’21, The Fourteenth ACM International Conference on Web Search and Data Mining, Virtual Event, Israel, March 8-12, 2021… [find](https://scholar.google.com/scholar?q=Gaole+He%2C+Yunshi+Lan%2C+Jing+Jiang%2C+Wayne+Xin+Zhao%2C+and+Ji%2DRong+Wen%2E+2021%2E+Improving+multi%2Dhop+knowledge+base+question+answering+by+learning+intermediate+supervision+signals%2E+In+WSDM+%E2%80%9921%2C+The+Fourteenth)
13. Xiaoxin He, Yijun Tian, Yifei Sun, Nitesh V. Chawla, Thomas Laurent, Yann LeCun, Xavier Bresson, and Bryan Hooi. 2024. [G-retriever: Retrieval-augmented generation for textual graph understanding and question answering](https://md.research.elamur.ai/free/en/papers/he-2024-g-retriever-retrieval-augmented-generation/).
14. Boran Jiang, Yuqi Wang, Yi Luo, Dawei He, Peng Cheng, and Liangcai Gao. 2024. Reasoning on efficient knowledge paths: Knowledge graph guides large language model for domain question answering. In IEEE International Conference on Knowledge Graph, ICKG 2023, Shanghai, China, December 1-2, 2023, pages… [find](https://scholar.google.com/scholar?q=Boran+Jiang%2C+Yuqi+Wang%2C+Yi+Luo%2C+Dawei+He%2C+Peng+Cheng%2C+and+Liangcai+Gao%2E+2024%2E+Reasoning+on+efficient+knowledge+paths%3A+Knowledge+graph+guides+large+language+model+for+domain+question+answering%2E+In+IEEE)
15. Jinhao Jiang, Kun Zhou, Zican Dong, Keming Ye, Xin Zhao, and Ji-Rong Wen. 2023a. Structgpt: A general framework for large language model to reason over structured data. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, EMNLP 2023, Singapore, December 6-10, 20… [find](https://scholar.google.com/scholar?q=Jinhao+Jiang%2C+Kun+Zhou%2C+Zican+Dong%2C+Keming+Ye%2C+Xin+Zhao%2C+and+Ji%2DRong+Wen%2E+2023a%2E+Structgpt%3A+A+general+framework+for+large+language+model+to+reason+over+structured+data%2E+In+Proceedings+of+the+2023+Conf)
16. Jinhao Jiang, Kun Zhou, Xin Zhao, Yang Song, Chen Zhu, Hengshu Zhu, and Ji-Rong Wen. 2025a. [Kg-agent: An efficient autonomous agent framework for complex reasoning over knowledge graph](https://md.research.elamur.ai/free/en/papers/jiang-2025-kg-agent-efficient-autonomous-agent/). In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)…
17. Jinhao Jiang, Kun Zhou, Xin Zhao, and Ji-Rong Wen. 2023b. Unikgqa: Unified retrieval and reasoning for solving multi-hop question answering over knowledge graph. In The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023. [find](https://scholar.google.com/scholar?q=Jinhao+Jiang%2C+Kun+Zhou%2C+Xin+Zhao%2C+and+Ji%2DRong+Wen%2E+2023b%2E+Unikgqa%3A+Unified+retrieval+and+reasoning+for+solving+multi%2Dhop+question+answering+over+knowledge+graph%2E+In+The+Eleventh+International+Conferen)
18. Xinke Jiang, Ruizhe Zhang, Yongxin Xu, Rihong Qiu, Yue Fang, Zhiyuan Wang, Jinyi Tang, Hongxin Ding, Xu Chu, Junfeng Zhao, and Yasha Wang. 2025b. Hykge: A hypothesis knowledge graph enhanced RAG framework for accurate and reliable medical llms responses. In Proceedings of the 63rd Annual Meeting of… [find](https://scholar.google.com/scholar?q=Xinke+Jiang%2C+Ruizhe+Zhang%2C+Yongxin+Xu%2C+Rihong+Qiu%2C+Yue+Fang%2C+Zhiyuan+Wang%2C+Jinyi+Tang%2C+Hongxin+Ding%2C+Xu+Chu%2C+Junfeng+Zhao%2C+and+Yasha+Wang%2E+2025b%2E+Hykge%3A+A+hypothesis+knowledge+graph+enhanced+RAG+frame)
19. Bowen Jin, Chulin Xie, Jiawei Zhang, Kashob Kumar Roy, Yu Zhang, Zheng Li, Ruirui Li, Xianfeng Tang, Suhang Wang, Yu Meng, and Jiawei Han. 2024. [Graph chain-of-thought: Augmenting large language models by reasoning on graphs](https://md.research.elamur.ai/free/en/papers/jin-2024-graph-chain-thought-augmenting-large/). In Findings of the Association for Computational Linguistics, ACL 2024, Ba…
20. Jiho Kim, Yeonsu Kwon, Yohan Jo, and Edward Choi. 2023. KG-GPT: A general framework for reasoning on knowledge graphs using large language models. In Findings of the Association for Computational Linguistics: EMNLP 2023, Singapore, December 6-10, 2023, pages 9410–9421. [find](https://scholar.google.com/scholar?q=Jiho+Kim%2C+Yeonsu+Kwon%2C+Yohan+Jo%2C+and+Edward+Choi%2E+2023%2E+KG%2DGPT%3A+A+general+framework+for+reasoning+on+knowledge+graphs+using+large+language+models%2E+In+Findings+of+the+Association+for+Computational+Ling)
21. 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. [find](https://scholar.google.com/scholar?q=Costas+Mavromatis+and+George+Karypis%2E+2025%2E+GNN%2DRAG%3A+graph+neural+retrieval+for+efficient+large+language+model+reasoning+on+knowledge+graphs%2E+In+Findings+of+the+Association+for+Computational+Linguisti)
22. Thomas N. Kipf and Max Welling. 2017. [Semi-supervised classification with graph convolutional networks](https://md.research.elamur.ai/free/en/papers/kipf-2016-semi-supervised-classification-graph-convolutional/). In 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24-26, 2017, Conference Track Proceedings.
23. Alexander Miller, Adam Fisch, Jesse Dodge, Amir-Hossein Karimi, Antoine Bordes, and Jason Weston. 2016. Key-value memory networks for directly reading documents. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 1400–1409. [find](https://scholar.google.com/scholar?q=Alexander+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+In+Proceedings+of+the+2016+Conference+)
24. 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](https://scholar.google.com/scholar?q=Yunshi+Lan%2C+Gaole+He%2C+Jinhao+Jiang%2C+Jing+Jiang%2C+Wayne+Xin+Zhao%2C+and+Ji%2DRong+Wen%2E+2021%2E+A+survey+on+complex+knowledge+base+question+answering%3A+Methods%2C+challenges+and+solutions%2E+In+Proceedings+of+the+T)
25. Yunshi Lan, Gaole He, Jinhao Jiang, Jing Jiang, Wayne Xin Zhao, and Ji-Rong Wen. 2023. Complex knowledge base question answering: A survey. IEEE Trans. Knowl. Data Eng., 35(11):11196–11215. [find](https://scholar.google.com/scholar?q=Yunshi+Lan%2C+Gaole+He%2C+Jinhao+Jiang%2C+Jing+Jiang%2C+Wayne+Xin+Zhao%2C+and+Ji%2DRong+Wen%2E+2023%2E+Complex+knowledge+base+question+answering%3A+A+survey%2E+IEEE+Trans%2E+Knowl%2E+Data+Eng%2E%2C+35%2811%29%3A11196%E2%80%9311215%2E)
26. Mufei Li, Siqi Miao, and Pan Li. 2025. Simple is effective: The roles of graphs and large language models in knowledge-graph-based retrieval-augmented generation. In The Thirteenth International Conference on Learning Representations, ICLR 2025, Singapore, April 24-28, 2025. [find](https://scholar.google.com/scholar?q=Mufei+Li%2C+Siqi+Miao%2C+and+Pan+Li%2E+2025%2E+Simple+is+effective%3A+The+roles+of+graphs+and+large+language+models+in+knowledge%2Dgraph%2Dbased+retrieval%2Daugmented+generation%2E+In+The+Thirteenth+International+Confe)
27. Zehan Li, Xin Zhang, Yanzhao Zhang, Dingkun Long, Pengjun Xie, and Meishan Zhang. 2023. [Towards general text embeddings with multi-stage contrastive learning](https://md.research.elamur.ai/free/en/papers/li-2023-towards-general-text-embeddings-multi/).
28. Guangyi Liu, Yongqi Zhang, Yong Li, and Quanming Yao. 2024. Explore then determine: A gnn-llm synergy framework for reasoning over knowledge graph. [find](https://scholar.google.com/scholar?q=Guangyi+Liu%2C+Yongqi+Zhang%2C+Yong+Li%2C+and+Quanming+Yao%2E+2024%2E+Explore+then+determine%3A+A+gnn%2Dllm+synergy+framework+for+reasoning+over+knowledge+graph%2E)
29. Dan Luo, Jiawei Sheng, Hongbo Xu, Lihong Wang, and Bin Wang. 2023. Improving complex knowledge base question answering with relation-aware subgraph retrieval and reasoning network. In International Joint Conference on Neural Networks, IJCNN 2023, Gold Coast, Australia, June 18-23, 2023, pages 1–8. [find](https://scholar.google.com/scholar?q=Dan+Luo%2C+Jiawei+Sheng%2C+Hongbo+Xu%2C+Lihong+Wang%2C+and+Bin+Wang%2E+2023%2E+Improving+complex+knowledge+base+question+answering+with+relation%2Daware+subgraph+retrieval+and+reasoning+network%2E+In+International+Jo)
30. 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. 2024a. Chatkbqa: A generate-then-retrieve framework for knowledge base question answering with fine-tuned large language models. In Findings of the… [find](https://scholar.google.com/scholar?q=Haoran+Luo%2C+Haihong+E%2C+Zichen+Tang%2C+Shiyao+Peng%2C+Yikai+Guo%2C+Wentai+Zhang%2C+Chenghao+Ma%2C+Guanting+Dong%2C+Meina+Song%2C+Wei+Lin%2C+Yifan+Zhu%2C+and+Anh+Tuan+Luu%2E+2024a%2E+Chatkbqa%3A+A+generate%2Dthen%2Dretrieve+framew)
31. Linhao Luo, Yuan-Fang Li, Gholamreza Haffari, and Shirui Pan. 2024b. Reasoning on graphs: Faithful and interpretable large language model reasoning. In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. [find](https://scholar.google.com/scholar?q=Linhao+Luo%2C+Yuan%2DFang+Li%2C+Gholamreza+Haffari%2C+and+Shirui+Pan%2E+2024b%2E+Reasoning+on+graphs%3A+Faithful+and+interpretable+large+language+model+reasoning%2E+In+The+Twelfth+International+Conference+on+Learning)
32. George L Nemhauser, Laurence A Wolsey, and Marshall L Fisher. 1978. An analysis of approximations for maximizing submodular set functions—i. Mathematical programming, 14(1):265–294. [find](https://scholar.google.com/scholar?q=George+L+Nemhauser%2C+Laurence+A+Wolsey%2C+and+Marshall+L+Fisher%2E+1978%2E+An+analysis+of+approximations+for+maximizing+submodular+set+functions%E2%80%94i%2E+Mathematical+programming%2C+14%281%29%3A265%E2%80%93294%2E)
33. Barlas Oguz, Xilun Chen, Vladimir Karpukhin, Stan Peshterliev, Dmytro Okhonko, Michael Sejr Schlichtkrull, Sonal Gupta, Yashar Mehdad, and Scott Yih. 2022. [Unik-qa: Unified representations of structured and unstructured knowledge for open-domain question answering](https://md.research.elamur.ai/free/en/papers/oguz-2022-unik-qa-unified-representations-structured/). In Findings of the Association for…
34. Boci Peng, Yongchao Liu, Xiaohe Bo, Jiaxin Guo, Yun Zhu, Xuanbo Fan, Chuntao Hong, and Yan Zhang. 2025a. M 3 gqa: A multi-entity multi-hop multi-setting graph question answering benchmark. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Pape… [find](https://scholar.google.com/scholar?q=Boci+Peng%2C+Yongchao+Liu%2C+Xiaohe+Bo%2C+Jiaxin+Guo%2C+Yun+Zhu%2C+Xuanbo+Fan%2C+Chuntao+Hong%2C+and+Yan+Zhang%2E+2025a%2E+M+3+gqa%3A+A+multi%2Dentity+multi%2Dhop+multi%2Dsetting+graph+question+answering+benchmark%2E+In+Proceedi)
35. Boci Peng, Yongchao Liu, Xiaohe Bo, Sheng Tian, Baokun Wang, Chuntao Hong, and Yan Zhang. 2024. Subgraph retrieval enhanced by graph-text alignment for commonsense question answering. In Machine Learning and Knowledge Discovery in Databases. Research Track - European Conference, ECML PKDD 2024, Viln… [find](https://scholar.google.com/scholar?q=Boci+Peng%2C+Yongchao+Liu%2C+Xiaohe+Bo%2C+Sheng+Tian%2C+Baokun+Wang%2C+Chuntao+Hong%2C+and+Yan+Zhang%2E+2024%2E+Subgraph+retrieval+enhanced+by+graph%2Dtext+alignment+for+commonsense+question+answering%2E+In+Machine+Learn)
36. Boci Peng, Yun Zhu, Yongchao Liu, Xiaohe Bo, Haizhou Shi, Chuntao Hong, Yan Zhang, and Siliang Tang. 2025b. [Graph retrieval-augmented generation: A survey](https://md.research.elamur.ai/free/en/papers/peng-2024-graph-retrieval-augmented-generation-survey/). ACM Trans. Inf. Syst., 44(2).
37. Stephen E. Robertson and Hugo Zaragoza. 2009. The probabilistic relevance framework: BM25 and beyond. Found. Trends Inf. Retr., 3(4):333–389. [find](https://scholar.google.com/scholar?q=Stephen+E%2E+Robertson+and+Hugo+Zaragoza%2E+2009%2E+The+probabilistic+relevance+framework%3A+BM25+and+beyond%2E+Found%2E+Trends+Inf%2E+Retr%2E%2C+3%284%29%3A333%E2%80%93389%2E)
38. Apoorv Saxena, Adrian Kochsiek, and Rainer Gemulla. 2022. Sequence-to-sequence knowledge graph completion and question answering. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2022, Dublin, Ireland, May 22-27, 2022, pages 2814… [find](https://scholar.google.com/scholar?q=Apoorv+Saxena%2C+Adrian+Kochsiek%2C+and+Rainer+Gemulla%2E+2022%2E+Sequence%2Dto%2Dsequence+knowledge+graph+completion+and+question+answering%2E+In+Proceedings+of+the+60th+Annual+Meeting+of+the+Association+for+Compu)
39. Apoorv Saxena, Aditay Tripathi, and Partha P. Talukdar. 2020. [Improving multi-hop question answering over knowledge graphs using knowledge base embeddings](https://md.research.elamur.ai/free/en/papers/saxena-2020-improving-multi-hop-question-answering/). In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, ACL 2020, Online, July 5-10, 2020, pages 4498–4507.…
40. Xiangqing Shen, Fanfan Wang, and Rui Xia. 2025. Reason-align-respond: Aligning llm reasoning with knowledge graphs for kgqa. [find](https://scholar.google.com/scholar?q=Xiangqing+Shen%2C+Fanfan+Wang%2C+and+Rui+Xia%2E+2025%2E+Reason%2Dalign%2Drespond%3A+Aligning+llm+reasoning+with+knowledge+graphs+for+kgqa%2E)
41. Xintao Wang, Qianwen Yang, Yongting Qiu, Jiaqing Liang, Qianyu He, Zhouhong Gu, Yanghua Xiao, and Wei Wang. 2023b. Knowledgpt: Enhancing large language models with retrieval and storage access on knowledge bases. [find](https://scholar.google.com/scholar?q=Xintao+Wang%2C+Qianwen+Yang%2C+Yongting+Qiu%2C+Jiaqing+Liang%2C+Qianyu+He%2C+Zhouhong+Gu%2C+Yanghua+Xiao%2C+and+Wei+Wang%2E+2023b%2E+Knowledgpt%3A+Enhancing+large+language+models+with+retrieval+and+storage+access+on+know)
42. Jiaxin Shi, Shulin Cao, Lei Hou, Juanzi Li, and Hanwang Zhang. 2021. Transfernet: An effective and transparent framework for multi-hop question answering over relation graph. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, EMNLP 2021, Virtual Event / Punta… [find](https://scholar.google.com/scholar?q=Jiaxin+Shi%2C+Shulin+Cao%2C+Lei+Hou%2C+Juanzi+Li%2C+and+Hanwang+Zhang%2E+2021%2E+Transfernet%3A+An+effective+and+transparent+framework+for+multi%2Dhop+question+answering+over+relation+graph%2E+In+Proceedings+of+the+202)
43. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Brian Ichter, Fei Xia, Ed H. Chi, Quoc V. Le, and Denny Zhou. 2022. [Chain-of-thought prompting elicits reasoning in large language models](https://md.research.elamur.ai/free/en/papers/wei-2022-chain-thought-prompting-elicits-reasoning/). In Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processi…
44. Haitian Sun, Tania Bedrax-Weiss, and William W. Cohen. 2019. Pullnet: Open domain question answering with iterative retrieval on knowledge bases and text. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural L… [find](https://scholar.google.com/scholar?q=Haitian+Sun%2C+Tania+Bedrax%2DWeiss%2C+and+William+W%2E+Cohen%2E+2019%2E+Pullnet%3A+Open+domain+question+answering+with+iterative+retrieval+on+knowledge+bases+and+text%2E+In+Proceedings+of+the+2019+Conference+on+Empi)
45. Yike Wu, Nan Hu, Sheng Bi, Guilin Qi, Jie Ren, Anhuan Xie, and Wei Song. 2023. Retrieve-rewrite-answer: A kg-to-text enhanced llms framework for knowledge graph question answering. [find](https://scholar.google.com/scholar?q=Yike+Wu%2C+Nan+Hu%2C+Sheng+Bi%2C+Guilin+Qi%2C+Jie+Ren%2C+Anhuan+Xie%2C+and+Wei+Song%2E+2023%2E+Retrieve%2Drewrite%2Danswer%3A+A+kg%2Dto%2Dtext+enhanced+llms+framework+for+knowledge+graph+question+answering%2E)
46. 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. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, Brussels, Belgium,… [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+In+Procee)
47. 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](https://scholar.google.com/scholar?q=Jiashuo+Sun%2C+Chengjin+Xu%2C+Lumingyuan+Tang%2C+Saizhuo+Wang%2C+Chen+Lin%2C+Yeyun+Gong%2C+Lionel+M%2E+Ni%2C+Heung%2DYeung+Shum%2C+and+Jian+Guo%2E+2024%2E+Think%2Don%2Dgraph%3A+Deep+and+responsible+reasoning+of+large+language+mode)
48. Alon Talmor and Jonathan Berant. 2018. [The web as a knowledge-base for answering complex questions](https://md.research.elamur.ai/free/en/papers/talmor-2018-web-as-knowledge-base-answering/). In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2018, New Orleans, Louisiana, USA, June 1-6…
49. Petar Veličković, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Liò, and Yoshua Bengio. 2018. Graph attention networks. [find](https://scholar.google.com/scholar?q=Petar+Velic%CC%8Ckovic%CC%81%2C+Guillem+Cucurull%2C+Arantxa+Casanova%2C+Adriana+Romero%2C+Pietro+Li%C3%B2%2C+and+Yoshua+Bengio%2E+2018%2E+Graph+attention+networks%2E)
50. Keheng Wang, Feiyu Duan, Sirui Wang, Peiguang Li, Yunsen Xian, Chuantao Yin, Wenge Rong, and Zhang Xiong. 2023a. Knowledge-driven cot: Exploring faithful reasoning in llms for knowledge-intensive question answering. [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+Xiong%2E+2023a%2E+Knowledge%2Ddriven+cot%3A+Exploring+faithful+reasoning+in+llms+for+knowledge%2Dintensive+ques)
51. Wenhui Wang, Hangbo Bao, Shaohan Huang, Li Dong, and Furu Wei. 2021. Minilmv2: Multi-head self-attention relation distillation for compressing pre-trained transformers. In Findings of the Association Siheng Xiong, Ali Payani, Ramana Kompella, and Faramarz Fekri. 2024. Large language models can learn… [find](https://scholar.google.com/scholar?q=Wenhui+Wang%2C+Hangbo+Bao%2C+Shaohan+Huang%2C+Li+Dong%2C+and+Furu+Wei%2E+2021%2E+Minilmv2%3A+Multi%2Dhead+self%2Dattention+relation+distillation+for+compressing+pre%2Dtrained+transformers%2E+In+Findings+of+the+Association+)
52. Siheng Xiong, Ali Payani, Yuan Yang, and Faramarz Fekri. 2025. [Deliberate reasoning in language models as structure-aware planning with an accurate world model](https://md.research.elamur.ai/free/en/papers/xiong-2025-deliberate-reasoning-language-models-as/). In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 31900– 31931.
53. Mufan Xu, Kehai Chen, Xuefeng Bai, Muyun Yang, Tiejun Zhao, and Min Zhang. 2025. Llm-based discriminative reasoning for knowledge graph question answering. [find](https://scholar.google.com/scholar?q=Mufan+Xu%2C+Kehai+Chen%2C+Xuefeng+Bai%2C+Muyun+Yang%2C+Tiejun+Zhao%2C+and+Min+Zhang%2E+2025%2E+Llm%2Dbased+discriminative+reasoning+for+knowledge+graph+question+answering%2E)
54. Rui Yang, Haoran Liu, Edison Marrese-Taylor, Qingcheng Zeng, Yuhe Ke, Wanxin Li, Lechao Cheng, Qingyu Chen, James Caverlee, Yutaka Matsuo, and Irene Li. 2024. Kg-rank: Enhancing large language models for medical QA with knowledge graphs and ranking techniques. In Proceedings of the 23rd Workshop on… [find](https://scholar.google.com/scholar?q=Rui+Yang%2C+Haoran+Liu%2C+Edison+Marrese%2DTaylor%2C+Qingcheng+Zeng%2C+Yuhe+Ke%2C+Wanxin+Li%2C+Lechao+Cheng%2C+Qingyu+Chen%2C+James+Caverlee%2C+Yutaka+Matsuo%2C+and+Irene+Li%2E+2024%2E+Kg%2Drank%3A+Enhancing+large+language+models+)
55. 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](https://md.research.elamur.ai/free/en/papers/yih-2016-value-semantic-parse-labeling-knowledge/). In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016, August 7-12, 2016, Berlin, Germany,…
56. 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. [find](https://scholar.google.com/scholar?q=Donghan+Yu%2C+Sheng+Zhang%2C+Patrick+Ng%2C+Henghui+Zhu%2C+Alexander+Hanbo+Li%2C+Jun+Wang%2C+Yiqun+Hu%2C+William+Yang+Wang%2C+Zhiguo+Wang%2C+and+Bing+Xiang%2E+2023%2E+Decaf%3A+Joint+decoding+of+answers+and+logical+forms+for+q)
57. In The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023. [find](https://scholar.google.com/scholar?q=In+The+Eleventh+International+Conference+on+Learning+Representations%2C+ICLR+2023%2C+Kigali%2C+Rwanda%2C+May+1%2D5%2C+2023%2E)
58. 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 Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2022,… [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+Proceedings+of+the+60t)
59. Jinman Zhao and Xueyan Zhang. 2024. Large language model is not a (multilingual) compositional relation reasoner. In First Conference on Language Modeling. [find](https://scholar.google.com/scholar?q=Jinman+Zhao+and+Xueyan+Zhang%2E+2024%2E+Large+language+model+is+not+a+%28multilingual%29+compositional+relation+reasoner%2E+In+First+Conference+on+Language+Modeling%2E)
60. Kaiyan Zhao, Qiyu Wu, Xin-Qiang Cai, and Yoshimasa Tsuruoka. 2024a. Leveraging multi-lingual positive instances in contrastive learning to improve sentence embedding. In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2024 - Volume 1:… [find](https://scholar.google.com/scholar?q=Kaiyan+Zhao%2C+Qiyu+Wu%2C+Xin%2DQiang+Cai%2C+and+Yoshimasa+Tsuruoka%2E+2024a%2E+Leveraging+multi%2Dlingual+positive+instances+in+contrastive+learning+to+improve+sentence+embedding%2E+In+Proceedings+of+the+18th+Confer)
61. Wayne Xin Zhao, Kun Zhou, Junyi Li, Tianyi Tang, Xiaolei Wang, Yupeng Hou, Yingqian Min, Beichen Zhang, Junjie Zhang, Zican Dong, Yifan Du, Chen Yang, Yushuo Chen, Zhipeng Chen, Jinhao Jiang, Ruiyang Ren, Yifan Li, Xinyu Tang, Zikang Liu, Peiyu Liu, Jian-Yun Nie, and Ji-Rong Wen. 2024b. [A survey of…](https://md.research.elamur.ai/free/en/papers/zhao-2023-survey-large-language-models/)

*Updated 1 November 2026*